Persistent per-project memory for Claude Code, Kiro & Cursor - plain markdown committed with your code, captured prompt-free, auto-injected at session start, recalled by meaning (local semantic search, zero API). Cross-project persona, cited recall, searchable session history.
- capability exposure inferred + 26
- recent drift inferred + 12
- tool safety inferred + 12
- trust mitigators mixed − 3
inferred mixed
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.
grade last moved 10h ago · see ecosystem CVEs →
- C · 55 → C · 47
- C · 47 → C · 55
- A · 0 → C · 47
No known CVEs for this server.
- high dangerous code
committed secret: Anthropic key · dynamic exec: new Function() · obfuscated payload: dynamic require()/import()
analyzed commit 1c1bbe3 · analyzer v33 · 5d ago
skills & prompt files 12
- agent-rules LH8PPL-core-memory-kit-1c1bbe3/.claude/agents/implementer.md
- agent-rules LH8PPL-core-memory-kit-1c1bbe3/.claude/agents/mechanic.md
- agent-rules LH8PPL-core-memory-kit-1c1bbe3/.claude/agents/reviewer.md
- agent-rules LH8PPL-core-memory-kit-1c1bbe3/CLAUDE.md
- skill LH8PPL-core-memory-kit-1c1bbe3/plugin/skills/bootstrap/SKILL.md
- skill LH8PPL-core-memory-kit-1c1bbe3/plugin/skills/memory-search/SKILL.md
- skill LH8PPL-core-memory-kit-1c1bbe3/plugin/skills/memory-write/SKILL.md
- skill LH8PPL-core-memory-kit-1c1bbe3/plugin/skills/troubleshooting/SKILL.md
- agent-rules LH8PPL-core-memory-kit-1c1bbe3/template/.claude/commands/tour.md
- skill LH8PPL-core-memory-kit-1c1bbe3/template/.claude/skills/memory-search/SKILL.md
- skill LH8PPL-core-memory-kit-1c1bbe3/template/.claude/skills/memory-write/SKILL.md
- skill LH8PPL-core-memory-kit-1c1bbe3/template/.claude/skills/troubleshooting/SKILL.md
danger signals9
- dynamic code execution new Function() LH8PPL-core-memory-kit-1c1bbe3/tests/cli-viewer.test.js :1137
for (const block of blocks) expect(() => new Function(block)).not.toThrow(); - committed secret Anthropic key LH8PPL-core-memory-kit-1c1bbe3/docs/process/cut-gate-cursor.md :558
sk-ant…(46 chars, redacted) - committed secret Anthropic key LH8PPL-core-memory-kit-1c1bbe3/docs/process/cut-gate-kiro-cli.md :228
sk-ant…(46 chars, redacted) - committed secret Anthropic key LH8PPL-core-memory-kit-1c1bbe3/docs/process/cut-gate-kiro.md :328
sk-ant…(46 chars, redacted) - committed secret Anthropic key LH8PPL-core-memory-kit-1c1bbe3/docs/process/cut-gate.md :588
sk-ant…(46 chars, redacted) - committed secret Anthropic key LH8PPL-core-memory-kit-1c1bbe3/scripts/live-test.mjs :44
sk-ant…(46 chars, redacted) - committed secret Anthropic key LH8PPL-core-memory-kit-1c1bbe3/tests/cli-graduation.test.js :240
sk-ant…(73 chars, redacted) - committed secret Anthropic key LH8PPL-core-memory-kit-1c1bbe3/tests/cli-remember-rich.test.js :127
sk-ant…(93 chars, redacted) - committed secret Anthropic key LH8PPL-core-memory-kit-1c1bbe3/tests/cli-screen-then-mask.test.js :165
sk-ant…(49 chars, redacted)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:LH8PPL/claude-memory-kit/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 LH8PPL.