ClawAudit verdict
ask-a-human
Submits subjective questions to a disclosed crowdsourcing platform (ask-a-human.com) using a user-configured agent ID; network_out matches the stated purpose, all API endpoints are documented, and responses come from opted-in volunteers.
⚠ 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
network_out
Findings (3)
Popular HTTP library — network access
examples/usage.md · code · got
Accesses shell history/config
README.md · prose · downgraded · ~/.zshrc
Accesses OpenClaw config/secrets directly
README.md · prose · downgraded · ~/.openclaw/openclaw.json
Permissions & capabilities
Requires 1 environment variable.
network_out Is this flag fair?
Thanks — recorded.