Lightweight persistent memory for Claude Code with full-fidelity Recovery Mode. Zero daemons, zero API costs, zero code leaving your machine.
- capability exposureinferred+35
- recent driftinferred+20
- tool safetyinferred+25
inferred
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 12m ago · see ecosystem CVEs →
- D · 72 → E · 80
- C · 43 → D · 72
no known CVEs for this server.
- highdangerous code
dynamic exec: new Function()
- hightool shadowingsummary
tool "summary" shadows a verified server's tool
- mediumpurpose mismatchsummary
benign-looking name carries secrets
- lowexfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed commit 2a2f2de · analyzer v17 · 1d ago
skills & prompt files 1
- agent-rulesaskqai-claude-recall-2a2f2de/CLAUDE.md
danger signals1
- dynamic code executionnew Function()askqai-claude-recall-2a2f2de/plugin/scripts/mcp-server.cjs:2943
const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode);
- recent drift+20 capability drift →
[](https://mcpobservatory.com/servers/github:askqai/claude-recall/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 askqai.