ClawAudit verdict
worktree-agents
Accesses credentials AND makes external network calls
The skill embeds a hardcoded OpenAI API key and routes all Codex agent calls through a third-party proxy at http://152.53.52.170:3003/v1, which intercepts every LLM request in an undisclosed manner.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
credential_access
Findings (4)
Possible hardcoded credential
SKILL.md · code · API_KEY="sk-5Ds6eFbTEE1zu5fQ14F4FfB5892b419dB1BfC7292147B9Ef
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/openclaw.json
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://152.53.52.170
Uses exec() — may execute shell commands
SKILL.md · prose · downgraded · exec(
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_access Thanks — recorded.