ClawAudit verdict
cli-worker
The skill delegates coding tasks to Kimi CLI agents in isolated git worktrees, requiring Kimi CLI to be installed and authenticated separately, and does not handle credentials itself.
⚠ 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.
Findings (6)
Accesses sensitive system files
SECURITY.md · prose · downgraded · /etc/passwd
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
References child_process — can spawn system processes
bin/auth/verify.js · prose · downgraded · child_process
Dynamic import() — loads module at runtime
bin/cli/main.js · prose · downgraded · import("
Uses spawn() — can execute external programs
bin/providers/claude.js · prose · downgraded · spawn(
Accesses sensitive environment variables
bin/providers/claude.js · prose · downgraded · process.env.ANTHROPIC_API_KEY
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.
Is this flag fair?
Thanks — recorded.