Caveat verdict

grok-swarm

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

Multi-agent code analysis skill using OpenRouter API key for its stated purpose of coordinating Grok agents; no suspicious exfiltration or redirect patterns beyond the documented functionality.

⚠ 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.

40
security
30
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (7)

Pattern match medium

subprocess execution — runs system commands from Python

bridge/cli.py · prose · downgraded · subprocess.run(

Pattern match medium

subprocess with shell=True — command injection vector

bridge/cli.py · prose · downgraded · subprocess.run( args.execute, shell=True

Pattern match medium

References child_process — can spawn system processes

bridge/index.js · prose · downgraded · child_process

Pattern match medium

Uses spawn() — can execute external programs

bridge/index.js · prose · downgraded · spawn(

Pattern match medium

Accesses OpenClaw config/secrets directly

install.sh · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match low

pip3 install — installs Python packages at runtime

bridge/grok_bridge.py · prose · downgraded · pip3 install

Pattern match low

Python os.environ.get — reads environment variable

bridge/grok_bridge.py · prose · downgraded · os.environ.get(

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.

network_incredential_accesspackage_install

Is this flag fair?

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