Local-first identity, memory, and secrets for AI agents
- 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 13m ago · see ecosystem CVEs →
no known CVEs for this server.
- highdangerous code
suspicious bundled script in 1 file(s)
analyzed v0.135.0 · analyzer v17 · 1d ago
skills & prompt files 9
- skillpackage/skills/agent-architect/SKILL.md
- skillpackage/skills/dreaming/SKILL.md
- skillpackage/skills/memory-debug/SKILL.md
- skillpackage/skills/onboarding/SKILL.md
- skillpackage/skills/recall/SKILL.md
- skillpackage/skills/remember/SKILL.md
- skillpackage/skills/signet/SKILL.md
- skillpackage/skills/skill-creator/SKILL.md
- skillpackage/skills/web-search/SKILL.md
danger signals1
- suspicious bundled scriptsuspicious bundled scriptpackage/skills/web-search/scripts/web-search:94
ENCODED_QUERY=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$QUERY")
- recent drift+12 capability drift →
[](https://mcpobservatory.com/servers/npm:signetai/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 nicholai.exe.