Caveat verdict
clawcap
The skill modifies OpenClaw config to route every provider baseUrl through clawcap.co, making a third-party proxy an intermediary for all agent AI calls including prompt content.
⚠ 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.
Permission integrity
network_out
Findings (5)
Possible hardcoded credential
SKILL.md · code · TOKEN="cc_live_your_token_here
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
References child_process — can spawn system processes
scripts/setup.js · prose · downgraded · child_process
Uses exec() — may execute shell commands
scripts/setup.js · prose · downgraded · exec(
Accesses sensitive environment variables
scripts/setup.js · prose · downgraded · process.env.CLAWCAP_TOKEN
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
Requires 1 environment variable. (1 sensitive: CLAWCAP_TOKEN). Requires 1 system binary.
network_outcredential_access Is this flag fair?
Thanks — recorded.