Brokk Bifrost Searchtools — the complete, unedited output of the deterministic mcptrustchecker engine v1.5.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.5.0",
"methodologyVersion": "mcptrustchecker-1.4"
},
"target": {
"id": "brokk-bifrost-searchtools",
"source": {
"kind": "package",
"origin": "brokk-bifrost-searchtools"
},
"server": {
"name": "brokk-bifrost-searchtools"
}
},
"grade": "C",
"score": {
"score": 71,
"threatScore": 78,
"grade": "C",
"band": "C",
"gateCap": "C",
"categorySubtotals": {
"injection": 0,
"exfiltration": 22,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"rawWeight": 22,
"confidenceMult": 1,
"diminishingFactor": 1,
"appliedPenalty": 22
},
{
"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": "repo",
"label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
"appliedPenalty": 1
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "source",
"label": "inspection depth (source) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [
"1 confirmed high finding → grade capped at C"
],
"methodologyVersion": "mcptrustchecker-1.6"
},
"capability": {
"level": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": false,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded AWS access key id in server code (python_tests/test_searchtools_client.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"description": "A live-looking AWS access key id is hardcoded in `python_tests/test_searchtools_client.py:1675`. Secrets in source ship to everyone who installs the package and are a direct credential leak.",
"remediation": "Remove the secret, rotate it, and load credentials from the environment or a secret store.",
"location": {
"kind": "server",
"name": "python_tests/test_searchtools_client.py"
},
"evidence": "AWS access key id: AKIA…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "aws-access-key",
"file": "python_tests/test_searchtools_client.py",
"line": 1675
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (scripts/voyage_sidecar.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`scripts/voyage_sidecar.py:170`): 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": "scripts/voyage_sidecar.py"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "scripts/voyage_sidecar.py",
"line": 170
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (tests/fixtures/policy-cli/project/src/app.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tests/fixtures/policy-cli/project/src/app.py:2`): 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": "tests/fixtures/policy-cli/project/src/app.py"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/fixtures/policy-cli/project/src/app.py",
"line": 2
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (editors/vscode/src/lifecycle.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`editors/vscode/src/lifecycle.ts: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": "editors/vscode/src/lifecycle.ts"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "editors/vscode/src/lifecycle.ts",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (editors/vscode/src/provisioning.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`editors/vscode/src/provisioning.ts: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": "editors/vscode/src/provisioning.ts"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "editors/vscode/src/provisioning.ts",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugins/bifrost-agent/amp-skills/bifrost-code-intelligence/bin/bifrost-launcher.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugins/bifrost-agent/amp-skills/bifrost-code-intelligence/bin/bifrost-launcher.mjs: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": "plugins/bifrost-agent/amp-skills/bifrost-code-intelligence/bin/bifrost-launcher.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugins/bifrost-agent/amp-skills/bifrost-code-intelligence/bin/bifrost-launcher.mjs",
"line": 3
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugins/bifrost-agent/bin/bifrost-launcher.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugins/bifrost-agent/bin/bifrost-launcher.mjs: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": "plugins/bifrost-agent/bin/bifrost-launcher.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugins/bifrost-agent/bin/bifrost-launcher.mjs",
"line": 3
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugins/bifrost-agent/test/launcher.test.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugins/bifrost-agent/test/launcher.test.mjs:2`): 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": "plugins/bifrost-agent/test/launcher.test.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugins/bifrost-agent/test/launcher.test.mjs",
"line": 2
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugins/bifrost-agent/test/package-contents.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugins/bifrost-agent/test/package-contents.mjs:2`): 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": "plugins/bifrost-agent/test/package-contents.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugins/bifrost-agent/test/package-contents.mjs",
"line": 2
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugins/bifrost-agent/test/packed-install.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugins/bifrost-agent/test/packed-install.mjs:2`): 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": "plugins/bifrost-agent/test/packed-install.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugins/bifrost-agent/test/packed-install.mjs",
"line": 2
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugins/bifrost-agent/test/sync-release-version.test.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugins/bifrost-agent/test/sync-release-version.test.mjs:2`): 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": "plugins/bifrost-agent/test/sync-release-version.test.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugins/bifrost-agent/test/sync-release-version.test.mjs",
"line": 2
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (python_tests/test_searchtools_client.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`python_tests/test_searchtools_client.py:63`): 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": "python_tests/test_searchtools_client.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "python_tests/test_searchtools_client.py",
"line": 63
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (scripts/generate-supplemental-third-party-notices.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`scripts/generate-supplemental-third-party-notices.mjs: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": "scripts/generate-supplemental-third-party-notices.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/generate-supplemental-third-party-notices.mjs",
"line": 3
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"brokk-bifrost-searchtools\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "brokk-bifrost-searchtools"
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "07805d9d6e5990237d4055fd5c801cd22274ac6b7825dadd586c284dfa534fb9",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 13,
"medium": 0,
"low": 0,
"info": 1
}
}
}