Caveat verdict

claude-code-collaboration

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

Multi-agent collaboration via local file queues between OpenClaw and Claude Code CLI; ANTHROPIC_BASE_URL pointing to Alibaba Cloud is a documented model provider configuration.

⚠ 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.

55
security
50
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · TOKEN="your-api-token

Pattern match medium

subprocess execution — runs system commands from Python

scripts/agent.py · prose · downgraded · subprocess.run(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class 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.

package_installnetwork_in

Is this flag fair?

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