ClawAudit verdict
OpenClaw 全能守护包
openclaw-guardian-suite
The install command runs a bash script sourced from an external payment server (skill.socialmore.net) without showing the script contents first, an unusual pattern that could introduce unreviewed code from a third-party monetization service.
⚠ 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 (5)
Pipe to python — executes piped content as Python code
lib/sdk/auth.sh · prose · downgraded · | python3
Possible hardcoded credential
lib/sdk/auth.sh · prose · downgraded · TOKEN="dry-run-token-$(date +%s)
Accesses OpenClaw config/secrets directly
lib/skills/config-modification/SKILL.md · code · ~/.openclaw/openclaw.json
Pipe to bash — executes piped content as shell commands
lib/skills/skill-safe-install/SKILL.md · prose · downgraded · |bash
References sudo — requests elevated privileges
lib/skills/skill-safe-install/SKILL.md · prose · downgraded · sudo
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/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.
network_in Is this flag fair?
Thanks — recorded.