Mcp Rss — 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": "mcp_rss",
"source": {
"kind": "package",
"origin": "mcp_rss"
},
"server": {
"name": "mcp_rss"
}
},
"grade": "A",
"score": {
"score": 94,
"threatScore": 96,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 3.6,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-UNI-005",
"category": "injection",
"severity": "medium",
"confidence": "heuristic",
"rawWeight": 9,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 3.6
},
{
"kind": "client",
"term": "capability-exposure",
"level": "minimal",
"label": "capability blast radius (minimal) — client exposure if the model is manipulated",
"appliedPenalty": 0
},
{
"kind": "client",
"term": "verification-discount",
"level": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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": "minimal",
"reasons": [],
"tags": []
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (3 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-UNI-005",
"title": "Hidden zero-width / joiner character in description",
"category": "injection",
"severity": "medium",
"confidence": "heuristic",
"description": "Found 2 zero-width / joiner character character(s) in the description of tool \"get_sources\". These are invisible to a human reviewer but are read verbatim by the model.",
"remediation": "Reject or normalize server metadata containing invisible/smuggling characters. Legitimate tool descriptions do not need them.",
"location": {
"kind": "tool",
"name": "get_sources",
"field": "description"
},
"evidence": "2× zero-width",
"owasp": "LLM01:2025 Prompt Injection",
"references": [
"https://unicode.org/reports/tr39/"
],
"data": {
"family": "zero-width",
"count": 2
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"mcp_rss\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "mcp_rss"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "get_content",
"tags": [],
"reasons": {}
},
{
"tool": "get_sources",
"tags": [],
"reasons": {}
},
{
"tool": "set_tag",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "bab61b9094817bf3ebe32e5116ff1979bbc10988b00b1fe1f8ba33f16bf1b49c",
"stats": {
"tools": 3,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 1,
"low": 0,
"info": 1
}
}
}