ClawAudit verdict
jun-invest-option-master-agent
The skill is for installing and upgrading an isolated agent workspace, with transparent use of capabilities and no malicious 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 (2)
Python os.getenv — reads environment variable
agent/invest_agent/integrations/futu/futu_adapter.py · prose · downgraded · os.getenv(
Python urllib.request — network access
agent/invest_agent/integrations/public/stooq.py · prose · downgraded · urllib.request
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.