ClawAudit verdict
reel-digest
The skill executes bash scripts for video analysis, which could potentially be exploited if the scripts are malicious.
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.
Findings (3)
subprocess execution โ runs system commands from Python
scripts/reel-digest.py ยท prose ยท downgraded ยท subprocess.run(
subprocess with shell=True โ command injection vector
scripts/reel-digest.py ยท prose ยท downgraded ยท subprocess.run(cmd, shell=True
Python urllib.request โ network access
scripts/reel-digest.py ยท prose ยท downgraded ยท urllib.request
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). 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.
Is this flag fair?
Thanks โ recorded.