Fetch — 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": "@yawlabs/fetch-mcp",
"source": {
"kind": "package",
"origin": "@yawlabs/fetch-mcp"
},
"server": {
"name": "@yawlabs/fetch-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": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"external-sink",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (15 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 (bin/fetch-mcp.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/fetch-mcp.mjs:57`): 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": "bin/fetch-mcp.mjs"
},
"evidence": "ync, spawn } from \"node:child_process\"; import { existsSync } from \"node:fs\"; import { constants, homedir } from \"node:o",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/fetch-mcp.mjs",
"line": 57,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([fetch_html_to_markdown, fetch_html_to_text, fetch_feed, fetch_links, fetch_meta, fetch_reader, fetch_robots, fetch_sitemap]) co-exist with external-action tools ([http_post]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
"remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
"location": {
"kind": "flow",
"name": "fetch_html_to_markdown → http_post"
},
"evidence": "untrusted [fetch_html_to_markdown, fetch_html_to_text, fetch_feed, fetch_links, fetch_meta, fetch_reader, fetch_robots, fetch_sitemap] → sinks [http_post]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"fetch_html_to_markdown",
"fetch_html_to_text",
"fetch_feed",
"fetch_links",
"fetch_meta",
"fetch_reader",
"fetch_robots",
"fetch_sitemap"
],
"sinks": [
"http_post"
]
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (bin/fetch-mcp.mjs)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`bin/fetch-mcp.mjs:227`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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": "bin/fetch-mcp.mjs"
},
"evidence": "= SERVER_ENTRY; await import(SERVER_URL.href); } const mode = (process.env.FETCH_MCP_RUNTIME ?? \"auto\").toLowerCase()",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "bin/fetch-mcp.mjs",
"line": 227,
"nonRuntime": false
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"fetch_html_to_markdown",
"fetch_html_to_text",
"fetch_feed",
"fetch_links",
"fetch_meta",
"fetch_reader",
"fetch_robots",
"fetch_sitemap"
],
"sensitiveSource": [],
"externalSink": [
"http_post"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "fetch_html_to_markdown",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "fetch_html_to_text",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "fetch_feed",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "http_get",
"tags": [],
"reasons": {}
},
{
"tool": "http_post",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"http_post\""
]
}
},
{
"tool": "http_put",
"tags": [],
"reasons": {}
},
{
"tool": "http_patch",
"tags": [],
"reasons": {}
},
{
"tool": "http_delete",
"tags": [],
"reasons": {}
},
{
"tool": "http_head",
"tags": [],
"reasons": {}
},
{
"tool": "http_options",
"tags": [],
"reasons": {}
},
{
"tool": "fetch_links",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "fetch_meta",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "fetch_reader",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "fetch_robots",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "fetch_sitemap",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
}
],
"surfaceDigest": "15a9d71c3c4b64fe44f546ad3e08a337ba7c3dd5228e1d92a9b64d291e8b48eb",
"stats": {
"tools": 15,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 1,
"medium": 2,
"low": 0,
"info": 0
}
}
}