AI agent project management — task boards, progress tracking, and cost reporting.
- capability exposureinferred+28
- tool safetyinferred+14
- trust mitigatorsmixed−8
inferredmixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 15m ago · see ecosystem CVEs →
no known CVEs for this server.
- highdangerous code
credential logged in 2 file(s)
- lowexfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed commit 09964a9 · analyzer v17 · 2d ago
skills & prompt files 2
danger signals2
- credential in logscredential in logGammell53-clawwork-mcp-09964a9/dist/init.js:136
console.log(` API Key: ${apiKey}`); - credential in logscredential in logGammell53-clawwork-mcp-09964a9/src/init.ts:175
console.log(` API Key: ${apiKey}`);
[](https://mcpobservatory.com/servers/github:Gammell53/clawwork-mcp/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of Gammell53.