Evidence-first memory for Claude Code, Codex, and the terminal. Kimetsu sits beside your AI agent, watches what actually solves problems, remembers it, and feeds the high-signal context back so the next run starts where the last one left off.
- capability exposureinferred+22
- recent driftinferred+12
- tool safetyinferred+12
- 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 →
- B · 19 → C · 43
- A · 0 → B · 19
No known CVEs for this server.
- highdangerous code
committed secret: Anthropic key, GitHub fine-grained PAT
analyzed commit fa9865f · analyzer v20 · 3h ago
danger signals9
- committed secretAnthropic keyRodCor-kimetsu-fa9865f/crates/kimetsu-agent/src/anthropic.rs:375
sk-ant…(51 chars, redacted) - committed secretAnthropic keyRodCor-kimetsu-fa9865f/crates/kimetsu-agent/src/claude_code.rs:1221
sk-ant…(51 chars, redacted) - committed secretAnthropic keyRodCor-kimetsu-fa9865f/crates/kimetsu-brain/src/ingest.rs:423
sk-ant…(51 chars, redacted) - committed secretAnthropic keyRodCor-kimetsu-fa9865f/crates/kimetsu-brain/src/project.rs:3243
sk-ant…(51 chars, redacted) - committed secretAnthropic keyRodCor-kimetsu-fa9865f/crates/kimetsu-brain/src/projector.rs:1225
sk-ant…(51 chars, redacted) - committed secretAnthropic keyRodCor-kimetsu-fa9865f/crates/kimetsu-brain/src/redact.rs:262
sk-ant…(51 chars, redacted) - committed secretGitHub fine-grained PATRodCor-kimetsu-fa9865f/crates/kimetsu-brain/src/redact.rs:310
github…(69 chars, redacted) - committed secretAnthropic keyRodCor-kimetsu-fa9865f/crates/kimetsu-brain/src/sync.rs:950
sk-ant…(51 chars, redacted) - committed secretAnthropic keyRodCor-kimetsu-fa9865f/crates/kimetsu-core/src/secret.rs:111
sk-ant…(38 chars, redacted)
- recent drift+12 capability drift →
[](https://mcpobservatory.com/servers/github:RodCor/kimetsu/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 RodCor.