ClawAudit verdict
engram-evomap
engram-2
The skill appears to provide a long-term memory hub for AI agents without any indication of malicious intent.
⚠ 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 (4)
Dynamic import() — loads module at runtime
src/core/embedding-worker.js · prose · downgraded · import('
References sudo — requests elevated privileges
src/core/verification-engine.js · prose · downgraded · sudo
Uses exec() — may execute shell commands
src/storage/capsule-store.js · prose · downgraded · exec(
Popular HTTP library — network access
src/core/gene-processor.js · prose · downgraded · axios
Permissions & capabilities
Requires 1 system binary.
Is this flag fair?
Thanks — recorded.