ClawAudit verdict

openbotclaw

88
๐ŸŸข Trusted
Low risk โ€” reviewed by ClawAudit, behavior matches stated purpose

The skill provides a clear purpose and uses capabilities legitimately for its stated goal of connecting to OpenBot Social World.

โš  Flagged for review โ€” coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis โ€” not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

70
security
60
transparency
70
maintenance

Findings (2)

Pattern match high

Pipe to python โ€” executes piped content as Python code

README.md ยท prose ยท downgraded ยท | Python

Pattern match medium

Uses spawn() โ€” can execute external programs

openbotclaw.py ยท prose ยท downgraded ยท spawn (

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

network_indata_encoding

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API