Cli — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.8.0",
"methodologyVersion": "mcptrustchecker-1.8"
},
"target": {
"id": "@phren/cli",
"source": {
"kind": "package",
"origin": "@phren/cli"
},
"server": {
"name": "@phren/cli"
}
},
"grade": "D",
"score": {
"score": 68,
"threatScore": 78,
"grade": "D",
"band": "D",
"categorySubtotals": {
"injection": 6.3,
"exfiltration": 0,
"permissions": 15.44,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 3.15
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.25,
"appliedPenalty": 1.58
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"kind": "client",
"term": "verification-discount",
"level": "source",
"label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
"appliedPenalty": 0
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "source",
"label": "inspection depth (source) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.8"
},
"capability": {
"level": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code",
"untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
"untrusted input can reach code execution"
],
"tags": [
"external-sink",
"code-exec",
"sensitive-source",
"untrusted-input"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (59 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-FLOW-002",
"title": "Completed toxic-flow trifecta across tools",
"category": "exfiltration",
"severity": "critical",
"confidence": "strong",
"description": "This server (without client built-ins) exposes a complete data-exfiltration chain: get_memory_detail → add_custom_hook → remove_custom_hook. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.",
"remediation": "Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.",
"location": {
"kind": "flow",
"name": "get_memory_detail → add_custom_hook → remove_custom_hook"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"get_memory_detail"
],
"sources": [
"add_custom_hook",
"add_project"
],
"sinks": [
"add_custom_hook",
"remove_custom_hook"
],
"path": [
"get_memory_detail",
"add_custom_hook",
"remove_custom_hook"
],
"edges": [
{
"from": "get_memory_detail",
"to": "add_custom_hook",
"kind": "agent-mediated"
},
{
"from": "add_custom_hook",
"to": "remove_custom_hook",
"kind": "agent-mediated"
}
],
"wired": false
}
},
{
"ruleId": "MTC-FLOW-003",
"title": "Read-and-egress in one tool: \"add_custom_hook\"",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tool \"add_custom_hook\" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.",
"remediation": "Separate reading from sending; require explicit user confirmation before egress of file/secret contents.",
"location": {
"kind": "flow",
"name": "add_custom_hook"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"tags": [
"external-sink",
"code-exec",
"sensitive-source"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"add_custom_hook\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"add_custom_hook\" appears to run shell commands or evaluate code (parameter \"command\"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "add_custom_hook"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"external-sink",
"code-exec",
"sensitive-source"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"remove_custom_hook\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"remove_custom_hook\" appears to run shell commands or evaluate code (parameter \"command\"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "remove_custom_hook"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli-hooks-git.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli-hooks-git.js:8`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/cli-hooks-git.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli-hooks-git.js",
"line": 8
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/extract.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/extract.js:13`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/cli/extract.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/extract.js",
"line": 13
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/govern.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/govern.js:235`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/cli/govern.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/govern.js",
"line": 235
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/namespaces-store.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/namespaces-store.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/cli/namespaces-store.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/namespaces-store.js",
"line": 3
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/namespaces-utils.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/namespaces-utils.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/cli/namespaces-utils.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/namespaces-utils.js",
"line": 3
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/ops.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/ops.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/cli/ops.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/ops.js",
"line": 3
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/session-git.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/session-git.js:5`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/cli/session-git.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/session-git.js",
"line": 5
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/team.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/team.js:7`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/cli/team.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/team.js",
"line": 7
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/content/validate.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/content/validate.js:4`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/content/validate.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/content/validate.js",
"line": 4
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/hooks.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/hooks.js:5`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/hooks.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/hooks.js",
"line": 5
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/embedding.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/embedding.js:178`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/embedding.js"
},
"evidence": "fetch(\"https://api.openai.com/v1/embeddings\"",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/embedding.js",
"line": 178
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/shared/search-fallback.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/shared/search-fallback.js:88`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/shared/search-fallback.js"
},
"evidence": "exec(`SELECT rowid, project, filename, type, content, path FROM docs WHERE ${",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/shared/search-fallback.js",
"line": 88
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"add_custom_hook\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"add_custom_hook\" takes a command-shaped parameter \"command\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "add_custom_hook",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"remove_custom_hook\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"remove_custom_hook\" takes a command-shaped parameter \"command\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "remove_custom_hook",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/data/access.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/data/access.js:114`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/data/access.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/data/access.js",
"line": 114
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/init/setup.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/init/setup.js:45`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/init/setup.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/init/setup.js",
"line": 45
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/link/context.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/link/context.js:28`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/link/context.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/link/context.js",
"line": 28
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/link/link.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/link/link.js:50`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/link/link.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/link/link.js",
"line": 50
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/link/skills.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/link/skills.js:19`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/link/skills.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/link/skills.js",
"line": 19
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/phren-paths.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/phren-paths.js:95`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/phren-paths.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/phren-paths.js",
"line": 95
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/profile-store.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/profile-store.js:57`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/profile-store.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/profile-store.js",
"line": 57
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/project-config.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/project-config.js:65`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/project-config.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/project-config.js",
"line": 65
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/shared/index.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/shared/index.js:45`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/shared/index.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/shared/index.js",
"line": 45
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/store-registry.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/store-registry.js:43`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/store-registry.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/store-registry.js",
"line": 43
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"add_custom_hook\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"add_custom_hook\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "add_custom_hook"
},
"data": {
"tags": [
"external-sink",
"code-exec",
"sensitive-source"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"remove_custom_hook\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"remove_custom_hook\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "remove_custom_hook"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path\" on \"add_project\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"add_project\" takes a path parameter \"path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "add_project",
"field": "inputSchema.properties.path"
},
"data": {
"param": "path"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"get_memory_detail"
],
"sensitiveSource": [
"add_custom_hook",
"add_project"
],
"externalSink": [
"add_custom_hook",
"remove_custom_hook"
],
"selfContained": false,
"path": [
"get_memory_detail",
"add_custom_hook",
"remove_custom_hook"
],
"pathWired": false,
"description": "A cross-tool exfiltration chain exists: get_memory_detail → add_custom_hook → remove_custom_hook."
},
{
"id": "flow-2",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"add_custom_hook"
],
"externalSink": [
"add_custom_hook"
],
"selfContained": true,
"description": "Tool \"add_custom_hook\" both reads sensitive data and can send it externally."
}
],
"capabilities": [
{
"tool": "get_config",
"tags": [],
"reasons": {}
},
{
"tool": "set_config",
"tags": [],
"reasons": {}
},
{
"tool": "export_project",
"tags": [],
"reasons": {}
},
{
"tool": "import_project",
"tags": [],
"reasons": {}
},
{
"tool": "manage_project",
"tags": [],
"reasons": {}
},
{
"tool": "auto_extract_findings",
"tags": [],
"reasons": {}
},
{
"tool": "add_finding",
"tags": [],
"reasons": {}
},
{
"tool": "supersede_finding",
"tags": [],
"reasons": {}
},
{
"tool": "retract_finding",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_contradiction",
"tags": [],
"reasons": {}
},
{
"tool": "get_contradictions",
"tags": [],
"reasons": {}
},
{
"tool": "edit_finding",
"tags": [],
"reasons": {}
},
{
"tool": "remove_finding",
"tags": [],
"reasons": {}
},
{
"tool": "push_changes",
"tags": [],
"reasons": {}
},
{
"tool": "search_fragments",
"tags": [],
"reasons": {}
},
{
"tool": "get_related_docs",
"tags": [],
"reasons": {}
},
{
"tool": "read_graph",
"tags": [],
"reasons": {}
},
{
"tool": "link_findings",
"tags": [],
"reasons": {}
},
{
"tool": "cross_project_fragments",
"tags": [],
"reasons": {}
},
{
"tool": "list_hooks",
"tags": [],
"reasons": {}
},
{
"tool": "toggle_hooks",
"tags": [],
"reasons": {}
},
{
"tool": "add_custom_hook",
"tags": [
"external-sink",
"code-exec",
"sensitive-source"
],
"reasons": {
"external-sink": [
"parameter \"webhook\""
],
"code-exec": [
"parameter \"command\""
],
"sensitive-source": [
"parameter \"secret\""
]
}
},
{
"tool": "remove_custom_hook",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"command\""
]
}
},
{
"tool": "pin_memory",
"tags": [],
"reasons": {}
},
{
"tool": "get_truths",
"tags": [],
"reasons": {}
},
{
"tool": "memory_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "get_notes",
"tags": [],
"reasons": {}
},
{
"tool": "add_note",
"tags": [],
"reasons": {}
},
{
"tool": "edit_note",
"tags": [],
"reasons": {}
},
{
"tool": "remove_note",
"tags": [],
"reasons": {}
},
{
"tool": "promote_note",
"tags": [],
"reasons": {}
},
{
"tool": "add_project",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"path\""
]
}
},
{
"tool": "health_check",
"tags": [],
"reasons": {}
},
{
"tool": "doctor_fix",
"tags": [],
"reasons": {}
},
{
"tool": "list_hook_errors",
"tags": [],
"reasons": {}
},
{
"tool": "get_review_queue",
"tags": [],
"reasons": {}
},
{
"tool": "manage_review_item",
"tags": [],
"reasons": {}
},
{
"tool": "get_memory_detail",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "search_knowledge",
"tags": [],
"reasons": {}
},
{
"tool": "get_project_summary",
"tags": [],
"reasons": {}
},
{
"tool": "list_projects",
"tags": [],
"reasons": {}
},
{
"tool": "get_findings",
"tags": [],
"reasons": {}
},
{
"tool": "store_list",
"tags": [],
"reasons": {}
},
{
"tool": "session_start",
"tags": [],
"reasons": {}
},
{
"tool": "session_end",
"tags": [],
"reasons": {}
},
{
"tool": "session_context",
"tags": [],
"reasons": {}
},
{
"tool": "session_history",
"tags": [],
"reasons": {}
},
{
"tool": "list_skills",
"tags": [],
"reasons": {}
},
{
"tool": "read_skill",
"tags": [],
"reasons": {}
},
{
"tool": "write_skill",
"tags": [],
"reasons": {}
},
{
"tool": "remove_skill",
"tags": [],
"reasons": {}
},
{
"tool": "toggle_skill",
"tags": [],
"reasons": {}
},
{
"tool": "get_tasks",
"tags": [],
"reasons": {}
},
{
"tool": "add_task",
"tags": [],
"reasons": {}
},
{
"tool": "complete_task",
"tags": [],
"reasons": {}
},
{
"tool": "remove_task",
"tags": [],
"reasons": {}
},
{
"tool": "update_task",
"tags": [],
"reasons": {}
},
{
"tool": "tidy_done_tasks",
"tags": [],
"reasons": {}
},
{
"tool": "pin_task",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "8a90a349ec21080750b9bae0ecdf9860ed1ab9a5268ae4a6ae75ac9a2a47c32e",
"stats": {
"tools": 59,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 13,
"medium": 14,
"low": 3,
"info": 0
}
}
}