ClawAudit verdict
aegis-shield
The skill provides a prompt-injection and data-exfiltration screening tool, but its modifications to memory require careful evaluation.
⚠ 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)
Pipe to bash — executes piped content as shell commands
openclaw-safe-memory-append.js · prose · downgraded · |bash
Pipe to sh — executes piped content as shell commands
openclaw-safe-memory-append.js · prose · downgraded · |sh
References sudo — requests elevated privileges
openclaw-safe-memory-append.js · prose · downgraded · sudo
References agent memory files
openclaw-safe-memory-append.js · prose · downgraded · MEMORY.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/C). 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.