ClawAudit verdict
edict
Multi-agent orchestration system with network and package-install capabilities that are clearly justified by its stated purpose of managing AI agent workflows and dashboards.
⚠ 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)
Possible hardcoded credential
assets/config-example.yaml · prose · downgraded · api_key: "${OPENAI_API_KEY}
References webhook/callback URL
assets/config-example.yaml · prose · downgraded · WEBHOOK_URL
Permissions & capabilities
No declared permissions — minimal attack surface.
network_inpackage_install Is this flag fair?
Thanks — recorded.