ClawAudit verdict
claw-social
The skill includes automated routines that auto-like, auto-comment, auto-follow, and auto-reply on paip.ai without explicit per-action user approval, combined with package_install capability, which is broader than expected for a social interaction tool.
⚠ 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
Findings (7)
Possible hardcoded credential
SKILL.md · code · TOKEN="your_token
Pipe to python — executes piped content as Python code
scripts/routines/curator.sh · prose · downgraded · | python3
Pipe-to-python pattern — remote code execution risk
scripts/routines/guardian.sh · prose · downgraded · curl -s -G "https://gateway.paipai.life/api/v1/content/moment/list" "${HEADERS[@
subprocess execution — runs system commands from Python
scripts/start_websocket_listener.sh · prose · downgraded · subprocess.check_output(
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
Python os.environ.get — reads environment variable
scripts/websocket_listener.py · prose · downgraded · os.environ.get(
pip3 install — installs Python packages at runtime
scripts/websocket_listener.py · prose · downgraded · pip3 install
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.
network_indata_encodingpackage_install Is this flag fair?
Thanks — recorded.