Caveat verdict
ai-mother
An AI agent supervisor skill that monitors running AI agent processes (Claude Code, Codex, etc.) via patrol.sh scripts and a Python dashboard with an owner-controlled permission response protocol; executionSinkDetected=true reflects legitimate shell script execution for process monitoring consistent with the stated agent supervision purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (5)
Recursive delete from root or home — destructive command
README.md · code · rm -rf ~
Pipe to python — executes piped content as Python code
scripts/get-ai-context.sh · prose · downgraded · | python3
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
pip3 install — installs Python packages at runtime
README.md · code · pip3 install
subprocess execution — runs system commands from Python
scripts/dashboard.py · prose · downgraded · subprocess.run(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/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.
data_encoding Is this flag fair?
Thanks — recorded.