ClawAudit verdict
pidan-memory
Local vector memory system using LanceDB and Ollama entirely on-device with no external network calls; executionSinkDetected reflects legitimate local CLI usage.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (6)
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
scripts/install_ollama.sh · prose · downgraded · curl -fsSL https://ollama.ai/install.sh | sh
Pipe to sh — executes piped content as shell commands
scripts/install_ollama.sh · prose · downgraded · | sh
References child_process — can spawn system processes
handler.ts · prose · downgraded · child_process
Uses spawn() — can execute external programs
handler.ts · prose · downgraded · spawn(
Python os.environ.get — reads environment variable
auto_memory.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.