ClawAudit verdict

taskflow

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

The skill provides structured project/task management and doesn't contain any malicious code.

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.

58
security
70
transparency
80
maintenance

Findings (4)

Pattern match high

Uses exec() โ€” may execute shell commands

SKILL.md ยท code ยท exec(

Confirmed in code medium

Accesses process.env โ€” reads environment variables

SKILL.md ยท code

Pattern match medium

Instructs covert action โ€” may act without user awareness

SKILL.md ยท prose ยท downgraded ยท silently

Pattern match low

Opens WebSocket connection

examples/DASHBOARD-HOWTO.md ยท prose ยท downgraded ยท WebSocket

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

credential_accessprocess_exec

Is this flag fair?

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