ClawAudit verdict
clawguard
clawguarddevin
The skill is a security scanner for OpenClaw/Clawdbot skills, detecting malicious patterns before installation, with no evidence of malicious behavior.
⚠ 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)
Uses eval() — can execute arbitrary code
SKILL.md · prose · downgraded · eval(
Uses exec() — may execute shell commands
SKILL.md · prose · downgraded · exec(
Uses spawn() — can execute external programs
SKILL.md · prose · downgraded · spawn(
Raw socket connection — low-level network access
SKILL.md · prose · downgraded · socket.connect(
Accesses .ssh directory
SKILL.md · prose · downgraded · .ssh/
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.