ClawAudit verdict

megacmd

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

The skill seems to be a CLI agent for MEGA.nz with proper security measures in place.

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.

80
security
60
transparency
70
maintenance

Findings (2)

Pattern match high

References sudo โ€” requests elevated privileges

README.md ยท code ยท sudo

Coarse signal โ€” prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("password") and emits it outward ("upload"). Phrased as prose with no trigger tokens โ€” a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md ยท 1. **Always check exit code**: `mega-command || echo "FAILED ($?)"` 2. **Escape `!` in links**: `mega-get https://mega.nz/#F\!ABcD\!Key ./dir` 3. **Master Key i

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

network_in

Is this flag fair?

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