ClawAudit verdict

ayao-workflow-agent

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

Multi-agent workflow orchestrator that coordinates Claude Code and Codex agents via tmux; the skill explicitly prohibits the orchestrator from modifying project files directly and uses local dispatch scripts, with no evidence of credential exfiltration or malicious behavior.

⚠ 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.

security

transparency

maintenance

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read

Findings (10)

Pattern match critical

Possible hardcoded credential

references/agent-swarm-playbook.md · code · token: "<secret>

Pattern match high

Accesses OpenClaw config/secrets directly

references/agent-swarm-playbook.md · code · ~/.openclaw/openclaw.json

Pattern match high

Pipe to python — executes piped content as Python code

scripts/dispatch.sh · prose · downgraded · | python3

Pattern match medium

Opens WebSocket connection

references/agent-swarm-playbook.md · code · WebSocket

Pattern match medium

References agent configuration files

references/agent-swarm-playbook.md · code · CLAUDE.md

Pattern match medium

subprocess execution — runs system commands from Python

scripts/health-check.sh · prose · downgraded · subprocess.run(

Pattern match medium

Instructs covert action — may act without user awareness

scripts/health-check.sh · prose · downgraded · silently

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/install-hooks.sh · prose · downgraded · http://127.0.0.1

Pattern match low

Base64 encoding/decoding

scripts/backends/nano-banana.sh · prose · downgraded · Base64Encode

Pattern match low

Python os.environ.get — reads environment variable

scripts/backends/stub.sh · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/D/F). 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.

file_read

Is this flag fair?

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