ClawAudit verdict
memory-engine
memory-engine-3layer
Three-layer anti-amnesia memory system using local SQLite/FTS5 and optional GitHub backup; executionSinkDetected is from documented shell commands with user-controlled credentials.
⚠ 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.
Permission integrity
package_install
agent_memory
Findings (5)
References agent memory files
SKILL.md · frontmatter · MEMORY.md
Accesses OpenClaw config/secrets directly
README.md · prose · downgraded · ~/.openclaw/openclaw.json
Reads files from sensitive system paths
scripts/_timezone.js · prose · downgraded · readFileSync('/etc
References child_process — can spawn system processes
scripts/memory-boot.js · prose · downgraded · child_process
Uses exec() — may execute shell commands
scripts/memory-index.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
No declared permissions — minimal attack surface.
agent_memorypackage_install Is this flag fair?
Thanks — recorded.