ClawAudit verdict
dual-brain-memory-guardian
The skill implements a dual-brain memory system with Markdown rules (left brain) and Pinecone episodic memory (right brain) for correction handling and semantic recall; executionSinkDetected reflects scripts/memory-cli.js which is the documented CLI for managing memory entries.
⚠ 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 (5)
Possible hardcoded credential
setup.md · code · API_KEY: "<set-in-your-secret-store>
References agent memory files
memory-template.md · code · memory.md
Dynamic import() — loads module at runtime
scripts/memory-cli.js · prose · downgraded · import("
References child_process — can spawn system processes
scripts/verify.js · prose · downgraded · child_process
Uses exec() — may execute shell commands
scripts/verify.js · prose · downgraded · exec(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: PINECONE_API_KEY). Requires 2 system binaries. (1 elevated: npm).
Is this flag fair?
Thanks — recorded.