ClawAudit verdict
redis-memory-system
The skill explicitly bypasses dmScope isolation by reading raw transcript JSONL files from the filesystem via cron, which is an unusual capability that could expose conversation data beyond intended scope, though no external exfiltration endpoint is present.
⚠ 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 (2)
Pipe to python — executes piped content as Python code
scripts/memory.sh · prose · downgraded · | python3
yum install — installs system packages
scripts/setup.sh · prose · downgraded · yum install
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.
dynamic_eval Is this flag fair?
Thanks — recorded.