ClawAudit verdict
aegis-protocol
The skill is a self-healing stability monitor with hardcoded system monitoring commands. It includes security audit details, indicating no user input injection, network exfiltration, credential theft, or data exfiltration.
⚠ 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 (8)
subprocess execution — runs system commands from Python
SECURITY_AUDIT.md · code · subprocess.run(
Pipe to python — executes piped content as Python code
FILES.md · prose · downgraded · | Python
Uses eval() — can execute arbitrary code
SECURITY_AUDIT.md · prose · downgraded · eval(
subprocess with shell=True — command injection vector
aegis-protocol.py · prose · downgraded · subprocess.run(cmd, shell=True
Instructs covert action — may act without user awareness
README.md · prose · downgraded · silently
Uses exec() — may execute shell commands
SECURITY_AUDIT.md · prose · downgraded · exec(
Accesses .ssh directory
SECURITY.md · prose · downgraded · .ssh/
Accesses cloud provider credentials
SECURITY.md · prose · downgraded · ~/.aws
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.
Is this flag fair?
Thanks — recorded.