ClawAudit verdict
avenir-web
Operates a browser automation framework (Playwright/Python) for web task execution; the skill instructs the agent to run user-directed tasks via clearly documented local scripts with no evidence of data exfiltration or hidden behavior.
⚠ 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.
Findings (4)
Possible hardcoded credential
README.md · code · API_KEY="your-key
os.system/popen — direct OS command execution
src/avenir_web/runtime/browser.py · prose · downgraded · os.system(
Python os.getenv — reads environment variable
example.py · prose · downgraded · os.getenv(
References agent configuration files
src/avenir_web/runner.py · prose · downgraded · agent_config
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.
Is this flag fair?
Thanks — recorded.