thoughtproof-reasoning-check

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill issues a runtime POST to https://api.thoughtproof.ai/v1/check whose returned verdict (ALLOW/BLOCK/UNCERTAIN) directly controls whether the agent proceeds with executing transactions, and the skill is designed to require this external check before action.