Kapilraghuwanshi Dev Tools — 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": "@kapilraghuwanshi/dev-tools-mcp",
"source": {
"kind": "package",
"origin": "@kapilraghuwanshi/dev-tools-mcp"
},
"server": {
"name": "@kapilraghuwanshi/dev-tools-mcp"
}
},
"grade": "A",
"score": {
"score": 90,
"threatScore": 94,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 6.3,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-INJ-URL-1",
"category": "exfiltration",
"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-1.13"
},
"capability": {
"level": "moderate",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"reads sensitive or local data"
],
"tags": [
"sensitive-source",
"untrusted-input"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (27 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-INJ-URL-1",
"title": "Suspicious external URL in tool metadata",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "A hardcoded link to a request/paste/webhook sink (or raw IP) appears in the description of tool \"dt_http_trace\". Tool metadata pointing the model at a fixed external endpoint is a data-exfiltration channel — the classic \"send the output to …\" poisoning.",
"remediation": "A legitimate tool takes its destination as a validated parameter; it does not hardcode a webhook/paste sink in its description.",
"location": {
"kind": "tool",
"name": "dt_http_trace",
"field": "description"
},
"evidence": "https://bit.ly/xyz",
"owasp": "LLM02:2025 Sensitive Information Disclosure"
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"dt_http_headers\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"dt_http_headers\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "dt_http_headers",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "dt_encode_decode",
"tags": [],
"reasons": {}
},
{
"tool": "dt_hash_string",
"tags": [],
"reasons": {}
},
{
"tool": "dt_generate_uuid",
"tags": [],
"reasons": {}
},
{
"tool": "dt_parse_jwt",
"tags": [],
"reasons": {}
},
{
"tool": "dt_diff_text",
"tags": [],
"reasons": {}
},
{
"tool": "dt_convert_case",
"tags": [],
"reasons": {}
},
{
"tool": "dt_format_json",
"tags": [],
"reasons": {}
},
{
"tool": "dt_regex_test",
"tags": [],
"reasons": {}
},
{
"tool": "dt_color_convert",
"tags": [],
"reasons": {}
},
{
"tool": "dt_timestamp_convert",
"tags": [],
"reasons": {}
},
{
"tool": "dt_url_parse",
"tags": [],
"reasons": {}
},
{
"tool": "dt_generate_password",
"tags": [],
"reasons": {}
},
{
"tool": "dt_unit_converter",
"tags": [],
"reasons": {}
},
{
"tool": "dt_lorem_ipsum",
"tags": [],
"reasons": {}
},
{
"tool": "dt_format_sql",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"sql_query\"",
"parameter \"sql\""
]
}
},
{
"tool": "dt_npm_info",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "dt_github_repo",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "dt_gitignore_gen",
"tags": [],
"reasons": {}
},
{
"tool": "dt_caniuse",
"tags": [],
"reasons": {}
},
{
"tool": "dt_my_ip",
"tags": [],
"reasons": {}
},
{
"tool": "dt_ip_info",
"tags": [],
"reasons": {}
},
{
"tool": "dt_dns_lookup",
"tags": [],
"reasons": {}
},
{
"tool": "dt_http_trace",
"tags": [],
"reasons": {}
},
{
"tool": "dt_http_headers",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "dt_ssl_check",
"tags": [],
"reasons": {}
},
{
"tool": "dt_port_check",
"tags": [],
"reasons": {}
},
{
"tool": "dt_whois_lookup",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "a2de180eaa58fa274429027ede19d51e96cb1585d1cb12792b23dec3d84f18c2",
"stats": {
"tools": 27,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 2,
"low": 0,
"info": 0
}
}
}