Local-first memory engine for AI coding agents. Persistent project memory that survives context loss, shared across Claude, Cursor, and Codex. Privacy-first, evidence-graded, human-arbitrated.
- capability exposure inferred + 35
- 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.
graded 1m ago · see ecosystem CVEs →
- B · 32 → C · 56
- B · 17 → B · 32
- A · 0 → B · 17
No known CVEs for this server.
- high dangerous code
dynamic exec: __import__(), __import__ sink · suspicious bundled script in 1 file(s)
analyzed commit a4549e0 · analyzer v28 · 1d ago
skills & prompt files 21
- agent-rules kanadhiayash-shiroe-a4549e0/.cursor/rules/shiroe.mdc
- agent-rules kanadhiayash-shiroe-a4549e0/.windsurfrules
- agent-rules kanadhiayash-shiroe-a4549e0/AGENTS.md
- agent-rules kanadhiayash-shiroe-a4549e0/CLAUDE.md
- agent-rules kanadhiayash-shiroe-a4549e0/GEMINI.md
- skill kanadhiayash-shiroe-a4549e0/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/budget-governor/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/caveman-handoff/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/contradiction-resolution/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/evidence-grader/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/fleet-activator/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/handoff-compiler/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/memory-import-export/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/parent-sync/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/pattern-to-skill/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/privacy-abstraction/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/project-setup/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/prompt-context-engine/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/skill-importer/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/skill-router/SKILL.md
- skill kanadhiayash-shiroe-a4549e0/skills/wiki-maintenance/SKILL.md
danger signals4
- dynamic code execution __import__() kanadhiayash-shiroe-a4549e0/benchmarks/external/harness.py :400
"plain_files": lambda: __import__( - dynamic code execution __import__() kanadhiayash-shiroe-a4549e0/shiroe/adapters/harnesses/base.py :64
mod = __import__(module_name, fromlist=[class_name]) - dynamic code execution __import__ sink kanadhiayash-shiroe-a4549e0/tests/test_ws5_external_harness.py :239
env={**__import__("os").environ, **env}, - suspicious bundled script suspicious bundled script kanadhiayash-shiroe-a4549e0/scripts/bootstrap-benchmark-host.sh :52
curl -fsSL https://ollama.com/install.sh | sh
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:kanadhiayash/zeref-memory-engine/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 kanadhiayash.