Loading the registry…
A MCP Server for the Model Context Protocol (MCP) spec
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
186 critical findings reported by cisco-skill-scanner, 184 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
npm: @mcpjam/mcp-spec @ 1.1.1, 0 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- @mcpjam/mcp-spec
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
8 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
0 findings · 0.5s
v2.0.11
1122 findings · 124.1s
v0.3.74
4 findings · 8.0s
v0.1.0
0 findings · 4.7s
v0.1.0
4 findings · 4.7s
v0.1.0
0 findings · 8.7s
v0.71.0
29 findings · 0.5s
v2.3.8
30 findings · 7.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.71.0
No container image was published for this artifact. What each scanner covers
0 findings · 0.0s
vv1.6.0
No Go modules were found in this artifact. What each scanner covers
0 findings · 0.1s
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 20, 2026 | Flagged36 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: completetrivy: completeosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 1,189 findings across every scanner that examined this package. None of the 186 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 1,082 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
30 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: FILE_MAGIC_MISMATCH, DATA_EXFIL_JS_NETWORK · Files: /repo/node_modules/mcp-proxy/src/fixtures/simple-stdio-proxy-server.ts, /repo/node_modules/fastmcp/src/FastMCP.oauth.test.ts, /repo/node_modules/fastmcp/src/FastMCP.test.ts · reported by cisco-skill-scanner
2 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: FILE_MAGIC_MISMATCH · Files: /repo/node_modules/fastmcp/src/examples/oauth-server.ts · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
30 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/node_modules/ajv/scripts/bundle.js, /repo/node_modules/ajv/scripts/compile-dots.js, /repo/node_modules/typescript/lib/_tsc.js and 5 more · reported by cisco-skill-scanner
24 FILE_MAGIC_MISMATCH
Files: /repo/node_modules/zod/v3/external.js, /repo/node_modules/zod/v4/core/json-schema.js, /repo/node_modules/zod-to-json-schema/dist/esm/parseTypes.js and 9 more · reported by cisco-skill-scanner
9 LOW_ANALYZABILITY
Files: /repo/node_modules/range-parser, /repo/node_modules/accepts, /repo/node_modules/media-typer and 6 more · reported by cisco-skill-scanner
4 OBFUSCATION_HEX_BLOB
Files: /repo/node_modules/file-type/core.js · reported by cisco-skill-scanner
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 CVE-2025-13466
Files:
816 The model's answer could not be read.
Rules: COMMAND_INJECTION_EVAL, COMMAND_INJECTION_JS_CHILD_PROCESS, COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR and 68 more · Files: /repo/node_modules/@types/node/child_process.d.ts, /repo/node_modules/@types/node/sqlite.d.ts, /repo/node_modules/@types/node/url.d.ts and 278 more · reported by cisco-skill-scanner, osv-scanner, trivy and 2 more
170 The review budget for this scan was already spent before these findings were reached.
Rules: LOW_ANALYZABILITY, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE and 5 more · Files: /repo/node_modules/serve-static, /repo/node_modules/forwarded, /repo/node_modules/type-is and 154 more · reported by cisco-skill-scanner, nerlo-install-instruction
95 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: DATA_EXFIL_JS_FS_ACCESS, DATA_EXFIL_JS_NETWORK · Files: /repo/node_modules/@types/node/fs.d.ts, /repo/node_modules/@types/node/readline.d.ts, /repo/node_modules/@types/node/stream.d.ts and 11 more · reported by cisco-skill-scanner
1 The model did not answer for these findings.
Rules: CVE-2026-9678 · Files: package-lock.json · reported by trivy
Critical command injection and potential shell execution risks
This artifact contains critical command injection vulnerabilities, including those related to `eval`, `child_process`, and `Function` constructor usage, which could lead to shell execution. Additionally, there are findings of exposed JWT tokens and potential hidden executable scripts. Several medium severity issues, such as exposed password variables and obfuscated code, also warrant attention.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
1 CVE-2025-15284
Files: package-lock.json · reported by trivy
1 CVE-2026-8723
Files: package-lock.json · reported by trivy
1 CVE-2026-9679
Files: package-lock.json · reported by trivy
1 GHSA-4992-7rv2-5pvq
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-j47w-4g3g-c36v
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-v3r7-h72x-cjcm
Files: /repo/package-lock.json · reported by osv-scanner
Showing 25 of 25; the rest are in the per-scanner reports above.