Caveat verdict
skill-guard
skill-guard-actor
Accesses credentials AND encodes data
The skill sends skill content and API keys (LAKERA_API_KEY, OPENCLAW_HOOKS_TOKEN) to an externally hosted Apify actor (TMjFBNFqIIUfCBf6K) and receives results back via a webhook; while the stated purpose is security scanning, routing skill content and auth tokens through a third-party cloud actor is genuinely unusual and creates data exposure risk.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND encodes data — may obfuscate stolen credentials
LLM02 · ASI03 · ASI04
Accesses credentials AND writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Permission integrity
file_read+write
Findings (4)
References webhook/callback URL
SKILL.md · frontmatter · WEBHOOK_URL
Base64 encoding/decoding
SKILL.md · code · BASE64_ENCODE
Accesses OpenClaw config/secrets directly
INTEGRATION.md · prose · downgraded · ~/.openclaw/openclaw.json
References tunneling service
INTEGRATION.md · code · ngrok
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 4 environment variables. (3 sensitive: APIFY_TOKEN, LAKERA_API_KEY, OPENCLAW_HOOKS_TOKEN).
network_incredential_accessdata_encodingfile_write Thanks — recorded.