ClawAudit verdict
clanker
The skill requires a private key for deployment, which is a sensitive piece of information.
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
package_install
agent_memory
Findings (2)
Pipe to python โ executes piped content as Python code
SKILL.md ยท prose ยท downgraded ยท | Python
Python os.environ.get โ reads environment variable
scripts/deploy.py ยท prose ยท downgraded ยท os.environ.get(
Permissions & capabilities
Requires 3 system binaries. (1 elevated: curl).
package_installagent_memory Is this flag fair?
Thanks โ recorded.