Minimal, secure personal AI agent — Claude Agent SDK + Telegram + MCP
- capability exposureinferred+26
- trust mitigatorsmixed−3
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 1m ago · see ecosystem CVEs →
- A · 3 → B · 23
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit cda2bf9 · analyzer v20 · 9h ago
skills & prompt files 2
- agent-ruleskossov-it-cakeagent-cda2bf9/CLAUDE.md
- agent-ruleskossov-it-cakeagent-cda2bf9/groups/main/CLAUDE.md
danger signals1
- suspicious endpointapi.telegram.orgkossov-it-cakeagent-cda2bf9/channels/telegram.ts:4
const res = await fetch(`https://api.telegram.org/bot${token}/${method}`, {
[](https://mcpobservatory.com/servers/github:kossov-it/cakeagent/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 kossov-it.