Knowledge Keeper — the complete, unedited output of the deterministic mcptrustchecker engine v1.13.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.13.0",
"methodologyVersion": "mcptrustchecker-1.13"
},
"target": {
"id": "@zsc-glitch/knowledge-keeper-mcp",
"source": {
"kind": "package",
"origin": "@zsc-glitch/knowledge-keeper-mcp"
},
"server": {
"name": "@zsc-glitch/knowledge-keeper-mcp"
}
},
"grade": "A",
"score": {
"score": 93,
"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": "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": [],
"methodologyVersion": "mcptrustchecker-1.13"
},
"capability": {
"level": "high",
"reasons": [
"can send data / act on an external service",
"can create, modify or delete files",
"can execute shell commands or code"
],
"tags": [
"file-write",
"code-exec",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (33 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-SRC-002",
"title": "Shell/command execution in server code (hermes-plugin/knowledge-keeper/__init__.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`hermes-plugin/knowledge-keeper/__init__.py:62`): 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": "hermes-plugin/knowledge-keeper/__init__.py"
},
"evidence": "self._proc = subprocess.Popen( [MCP_COMMAND, *MCP_ARGS], stdin=subprocess.PIP",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "hermes-plugin/knowledge-keeper/__init__.py",
"line": 62,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (hermes-plugin/knowledge-keeper/cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`hermes-plugin/knowledge-keeper/cli.py:66`): 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": "hermes-plugin/knowledge-keeper/cli.py"
},
"evidence": "try: result = subprocess.run( [\"npx\", \"-y\", \"@zsc-glitch/knowledge-keeper-mcp\"], input",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "hermes-plugin/knowledge-keeper/cli.py",
"line": 66,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/cloud-sync.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/cloud-sync.js:298`): 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/cloud-sync.js"
},
"evidence": "const response = await fetch(\"https://api.knowledge-keeper.dev/v1/license\", { headers: { Authorization: `Be",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/cloud-sync.js",
"line": 298,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-002",
"title": "Tool \"knowledge_unlink\" can modify the filesystem",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"knowledge_unlink\" can write, overwrite or delete files (keyword \"unlink\" in tool name). Verify it is scoped to a safe directory.",
"remediation": "Constrain file operations to an explicit, non-sensitive root; reject path traversal.",
"location": {
"kind": "tool",
"name": "knowledge_unlink"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"knowledge_unlink\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"knowledge_unlink\" 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": "knowledge_unlink"
},
"data": {
"tags": [
"file-write"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "knowledge_analytics_overview",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_analytics_insights",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_analytics_timeline",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_batch",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_bm25_search",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_bm25_stats",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_sync_status",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_cloud_sync",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_license",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_context",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_delete",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_duplicates",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_export",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_get_linked",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_get",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_graph_build",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_graph_query",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_graph_visualize",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_graph",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_hybrid_search",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_import",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_link",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_merge",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_recent",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_review",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_save",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_search",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_semantic_search",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_sync",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_tags",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_unlink",
"tags": [
"file-write"
],
"reasons": {
"file-write": [
"keyword \"unlink\" in tool name"
]
}
},
{
"tool": "knowledge_update",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_versions",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "d090f230aaa3bccb551683a134d782d17e18ca205af450142cf19869ada97680",
"stats": {
"tools": 33,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 2,
"low": 1,
"info": 0
}
}
}