Caveat verdict

gateway-manager

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Unified multi-instance OpenClaw gateway manager scanning local config paths and restarting services; all operations local and aligned with gateway management purpose.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

38
security
70
transparency
70
maintenance

Findings (5)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://127.0.0.1

Pattern match high

Writes to SKILL.md — self-modifying skill

SECURITY_RESPONSE.md · prose · downgraded · SKILL.md tells the agent to run the included scripts. The scripts read and write

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

References child_process — can spawn system processes

scripts/gateway-create.sh · prose · downgraded · child_process

Pattern match low

References agent memory files

scripts/gateway-delete.sh · prose · downgraded · MEMORY.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/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?

Check another skill Browse the registry Auditing your own skills or configs? Use the API