Graspful — the complete, unedited output of the deterministic mcptrustchecker engine v1.7.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.7.0",
"methodologyVersion": "mcptrustchecker-1.7"
},
"target": {
"id": "@graspful/mcp",
"source": {
"kind": "package",
"origin": "@graspful/mcp"
},
"server": {
"name": "@graspful/mcp"
}
},
"grade": "B",
"score": {
"score": 87,
"threatScore": 91,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 2.22,
"exfiltration": 0,
"permissions": 6.3,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-INJ-AUTH-1",
"category": "injection",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 1.2
},
{
"kind": "threat",
"ruleId": "MTC-INJ-AUTH-1",
"category": "injection",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 0.5,
"appliedPenalty": 0.6
},
{
"kind": "threat",
"ruleId": "MTC-INJ-AUTH-1",
"category": "injection",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 0.25,
"appliedPenalty": 0.3
},
{
"kind": "threat",
"ruleId": "MTC-INJ-AUTH-1",
"category": "injection",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 0.1,
"appliedPenalty": 0.12
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "client",
"term": "capability-exposure",
"level": "moderate",
"label": "capability blast radius (moderate) — client exposure if the model is manipulated",
"appliedPenalty": 3
},
{
"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-1.7"
},
"capability": {
"level": "moderate",
"reasons": [
"can send data / act on an external service"
],
"tags": [
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (10 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-007",
"title": "Unsafe deserialization (dist/index.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:102`): 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/index.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/index.js",
"line": 102
}
},
{
"ruleId": "MTC-INJ-AUTH-1",
"title": "Authority framing in tool metadata",
"category": "injection",
"severity": "low",
"confidence": "heuristic",
"description": "Authority framing in tool metadata detected in the description of tool \"graspful_import_course\". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.",
"remediation": "Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.",
"location": {
"kind": "tool",
"name": "graspful_import_course",
"field": "description"
},
"evidence": "IMPORTANT",
"owasp": "LLM01:2025 Prompt Injection",
"data": {
"kind": "authority"
}
},
{
"ruleId": "MTC-INJ-AUTH-1",
"title": "Authority framing in tool metadata",
"category": "injection",
"severity": "low",
"confidence": "heuristic",
"description": "Authority framing in tool metadata detected in the description of tool \"graspful_publish_course\". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.",
"remediation": "Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.",
"location": {
"kind": "tool",
"name": "graspful_publish_course",
"field": "description"
},
"evidence": "IMPORTANT",
"owasp": "LLM01:2025 Prompt Injection",
"data": {
"kind": "authority"
}
},
{
"ruleId": "MTC-INJ-AUTH-1",
"title": "Authority framing in tool metadata",
"category": "injection",
"severity": "low",
"confidence": "heuristic",
"description": "Authority framing in tool metadata detected in the description of tool \"graspful_import_brand\". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.",
"remediation": "Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.",
"location": {
"kind": "tool",
"name": "graspful_import_brand",
"field": "description"
},
"evidence": "IMPORTANT",
"owasp": "LLM01:2025 Prompt Injection",
"data": {
"kind": "authority"
}
},
{
"ruleId": "MTC-INJ-AUTH-1",
"title": "Authority framing in tool metadata",
"category": "injection",
"severity": "low",
"confidence": "heuristic",
"description": "Authority framing in tool metadata detected in the description of tool \"graspful_list_courses\". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.",
"remediation": "Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.",
"location": {
"kind": "tool",
"name": "graspful_list_courses",
"field": "description"
},
"evidence": "IMPORTANT",
"owasp": "LLM01:2025 Prompt Injection",
"data": {
"kind": "authority"
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"@graspful/mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "@graspful/mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "graspful_scaffold_course",
"tags": [],
"reasons": {}
},
{
"tool": "graspful_fill_concept",
"tags": [],
"reasons": {}
},
{
"tool": "graspful_validate",
"tags": [],
"reasons": {}
},
{
"tool": "graspful_review_course",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"publish\""
]
}
},
{
"tool": "graspful_import_course",
"tags": [],
"reasons": {}
},
{
"tool": "graspful_publish_course",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"publish\""
]
}
},
{
"tool": "graspful_describe_course",
"tags": [],
"reasons": {}
},
{
"tool": "graspful_create_brand",
"tags": [],
"reasons": {}
},
{
"tool": "graspful_import_brand",
"tags": [],
"reasons": {}
},
{
"tool": "graspful_list_courses",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "ae7fcf9862b47ce0ce5226fb812b8222add2b71d09c483750c6a09554c4a3306",
"stats": {
"tools": 10,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 1,
"low": 4,
"info": 1
}
}
}