ClawAudit verdict
mx-auto
The skill seems to be a lightweight router for local Runtime automation, handling tasks such as listing and running triggers, inspecting browser sandbox tabs/snapshots, and listing/showing/running local scripts. The capabilities are used legitimately and transparently for its purpose.
⚠ 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 (3)
Possible hardcoded credential
scripts/browser_sandbox_bridge.sh · prose · downgraded · token="${BROWSER_SANDBOX_BRIDGE_TOKEN:-${MX_APP_RUNTIME_ADMIN_TOKEN:-${RPA_RUNTI
HTTP request to bare IP address — common in malicious payloads
scripts/browser_sandbox_bridge.sh · prose · downgraded · http://127.0.0.1
References child_process — can spawn system processes
scripts/preflight_check.sh · prose · downgraded · child_process
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.