ClawAudit verdict
dead-or-not
The skill can write files and send emails, which are powerful capabilities. The usage seems legitimate but requires monitoring.
โ 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.
Permission integrity
file_read+write
Findings (1)
Python os.getenv โ reads environment variable
scripts/send_mail.py ยท prose ยท downgraded ยท os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class F). Final tier capped at Caution โ cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions โ minimal attack surface.
network_infile_write Is this flag fair?
Thanks โ recorded.