ClawAudit verdict
enterprise-ai-assistant-bundle
The skill is primarily a commercial advertisement for paid software (¥99–¥999) with WeChat/email contact info embedded, and while it installs packages and runs a deploy script, there is no concrete evidence of malicious exfiltration; the commercial nature and external contact channels warrant caution.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — 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
Findings (2)
os.system/popen — direct OS command execution
deploy.py · prose · downgraded · os.system(
Python os.getenv — reads environment variable
bot.py · prose · downgraded · os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.