Mnema — 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": "@felipesauer/mnema",
"source": {
"kind": "package",
"origin": "@felipesauer/mnema"
},
"server": {
"name": "@felipesauer/mnema"
}
},
"grade": "A",
"score": {
"score": 94,
"threatScore": 100,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "high",
"label": "capability blast radius (high) — client exposure if the model is manipulated",
"appliedPenalty": 6
},
{
"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": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (95 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-CAP-001",
"title": "Tool \"eval_report\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"eval_report\" appears to run shell commands or evaluate code (keyword \"eval\"). 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": "eval_report"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/storage/markdown/frontmatter.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/storage/markdown/frontmatter.js:18`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/storage/markdown/frontmatter.js"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/storage/markdown/frontmatter.js",
"line": 18
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/commands/serve-command.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/commands/serve-command.js:1`): 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/commands/serve-command.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/commands/serve-command.js",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/services/anchor/git-signed-anchor-provider.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/services/anchor/git-signed-anchor-provider.js:1`): 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/services/anchor/git-signed-anchor-provider.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/services/anchor/git-signed-anchor-provider.js",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/services/domain-event-dispatcher.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/services/domain-event-dispatcher.js:1`): 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/services/domain-event-dispatcher.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/services/domain-event-dispatcher.js",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/services/git-commit-service.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/services/git-commit-service.js:1`): 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/services/git-commit-service.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/services/git-commit-service.js",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/services/github-pr-service.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/services/github-pr-service.js:1`): 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/services/github-pr-service.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/services/github-pr-service.js",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/services/memory-staleness.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/services/memory-staleness.js:1`): 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/services/memory-staleness.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/services/memory-staleness.js",
"line": 1
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"eval_report\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"eval_report\" 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": "eval_report"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "agent_plan_create",
"tags": [],
"reasons": {}
},
{
"tool": "agent_plan_update_state",
"tags": [],
"reasons": {}
},
{
"tool": "agent_plans_list",
"tags": [],
"reasons": {}
},
{
"tool": "agent_run_start",
"tags": [],
"reasons": {}
},
{
"tool": "agent_run_end",
"tags": [],
"reasons": {}
},
{
"tool": "agent_run_resume",
"tags": [],
"reasons": {}
},
{
"tool": "agent_run_show",
"tags": [],
"reasons": {}
},
{
"tool": "audit_query",
"tags": [],
"reasons": {}
},
{
"tool": "audit_verify",
"tags": [],
"reasons": {}
},
{
"tool": "commands_list",
"tags": [],
"reasons": {}
},
{
"tool": "command_show",
"tags": [],
"reasons": {}
},
{
"tool": "context_bootstrap",
"tags": [],
"reasons": {}
},
{
"tool": "epic_coverage",
"tags": [],
"reasons": {}
},
{
"tool": "sprint_coverage",
"tags": [],
"reasons": {}
},
{
"tool": "decision_record",
"tags": [],
"reasons": {}
},
{
"tool": "decision_promote_from_note",
"tags": [],
"reasons": {}
},
{
"tool": "decision_promote_from_observation",
"tags": [],
"reasons": {}
},
{
"tool": "decision_show",
"tags": [],
"reasons": {}
},
{
"tool": "decisions_list",
"tags": [],
"reasons": {}
},
{
"tool": "decisions_impacting",
"tags": [],
"reasons": {}
},
{
"tool": "decision_supersede",
"tags": [],
"reasons": {}
},
{
"tool": "decision_accept",
"tags": [],
"reasons": {}
},
{
"tool": "decision_reject",
"tags": [],
"reasons": {}
},
{
"tool": "graph_dependencies",
"tags": [],
"reasons": {}
},
{
"tool": "task_depends_on",
"tags": [],
"reasons": {}
},
{
"tool": "task_depends_many",
"tags": [],
"reasons": {}
},
{
"tool": "tasks_ready",
"tags": [],
"reasons": {}
},
{
"tool": "task_dependencies",
"tags": [],
"reasons": {}
},
{
"tool": "drift_commits",
"tags": [],
"reasons": {}
},
{
"tool": "epic_show",
"tags": [],
"reasons": {}
},
{
"tool": "epics_list",
"tags": [],
"reasons": {}
},
{
"tool": "epic_create",
"tags": [],
"reasons": {}
},
{
"tool": "epic_update",
"tags": [],
"reasons": {}
},
{
"tool": "epic_add_task",
"tags": [],
"reasons": {}
},
{
"tool": "epic_close",
"tags": [],
"reasons": {}
},
{
"tool": "epic_remove",
"tags": [],
"reasons": {}
},
{
"tool": "epic_delete",
"tags": [],
"reasons": {}
},
{
"tool": "eval_report",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\""
]
}
},
{
"tool": "task_attach_evidence",
"tags": [],
"reasons": {}
},
{
"tool": "task_evidence",
"tags": [],
"reasons": {}
},
{
"tool": "evolve_report",
"tags": [],
"reasons": {}
},
{
"tool": "file_collisions",
"tags": [],
"reasons": {}
},
{
"tool": "metrics_flow",
"tags": [],
"reasons": {}
},
{
"tool": "focus",
"tags": [],
"reasons": {}
},
{
"tool": "history_get",
"tags": [],
"reasons": {}
},
{
"tool": "task_set_labels",
"tags": [],
"reasons": {}
},
{
"tool": "task_labels",
"tags": [],
"reasons": {}
},
{
"tool": "labels_list",
"tags": [],
"reasons": {}
},
{
"tool": "memory_record",
"tags": [],
"reasons": {}
},
{
"tool": "memory_show",
"tags": [],
"reasons": {}
},
{
"tool": "memories_list",
"tags": [],
"reasons": {}
},
{
"tool": "memory_archive",
"tags": [],
"reasons": {}
},
{
"tool": "memory_supersede",
"tags": [],
"reasons": {}
},
{
"tool": "memory_contradict",
"tags": [],
"reasons": {}
},
{
"tool": "note_add",
"tags": [],
"reasons": {}
},
{
"tool": "observation_record",
"tags": [],
"reasons": {}
},
{
"tool": "observations_list",
"tags": [],
"reasons": {}
},
{
"tool": "observation_archive",
"tags": [],
"reasons": {}
},
{
"tool": "tasks_query",
"tags": [],
"reasons": {}
},
{
"tool": "pr_status",
"tags": [],
"reasons": {}
},
{
"tool": "provenance",
"tags": [],
"reasons": {}
},
{
"tool": "run_diff",
"tags": [],
"reasons": {}
},
{
"tool": "search",
"tags": [],
"reasons": {}
},
{
"tool": "skill_suggest",
"tags": [],
"reasons": {}
},
{
"tool": "skill_record",
"tags": [],
"reasons": {}
},
{
"tool": "skill_show",
"tags": [],
"reasons": {}
},
{
"tool": "skill_diff",
"tags": [],
"reasons": {}
},
{
"tool": "skill_use",
"tags": [],
"reasons": {}
},
{
"tool": "skills_list",
"tags": [],
"reasons": {}
},
{
"tool": "skill_review_proposals",
"tags": [],
"reasons": {}
},
{
"tool": "skill_supersede",
"tags": [],
"reasons": {}
},
{
"tool": "snapshot_generate",
"tags": [],
"reasons": {}
},
{
"tool": "sprint_show",
"tags": [],
"reasons": {}
},
{
"tool": "sprints_list",
"tags": [],
"reasons": {}
},
{
"tool": "sprint_add_task",
"tags": [],
"reasons": {}
},
{
"tool": "sprint_create",
"tags": [],
"reasons": {}
},
{
"tool": "sprint_add_tasks",
"tags": [],
"reasons": {}
},
{
"tool": "sprint_start",
"tags": [],
"reasons": {}
},
{
"tool": "sprint_close",
"tags": [],
"reasons": {}
},
{
"tool": "sprint_cancel",
"tags": [],
"reasons": {}
},
{
"tool": "sprint_remove",
"tags": [],
"reasons": {}
},
{
"tool": "sprint_metric",
"tags": [],
"reasons": {}
},
{
"tool": "task_create",
"tags": [],
"reasons": {}
},
{
"tool": "task_assign",
"tags": [],
"reasons": {}
},
{
"tool": "task_claim",
"tags": [],
"reasons": {}
},
{
"tool": "task_release_claim",
"tags": [],
"reasons": {}
},
{
"tool": "task_create_many",
"tags": [],
"reasons": {}
},
{
"tool": "task_update",
"tags": [],
"reasons": {}
},
{
"tool": "tasks_list",
"tags": [],
"reasons": {}
},
{
"tool": "task_show",
"tags": [],
"reasons": {}
},
{
"tool": "task_actions",
"tags": [],
"reasons": {}
},
{
"tool": "wikilinks_lint",
"tags": [],
"reasons": {}
},
{
"tool": "wikilink_references",
"tags": [],
"reasons": {}
},
{
"tool": "sprint_lint",
"tags": [],
"reasons": {}
},
{
"tool": "epic_lint",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "bf8539a6e1dd18c3896376f3837cf4026826eedb5378393b7d807d8693f012a1",
"stats": {
"tools": 95,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 8,
"medium": 0,
"low": 1,
"info": 0
}
}
}