terms-of-service-generator

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). Yes — SKILL.md Step 1 explicitly instructs the agent to "Use WebFetch to visit the provided URL" to analyze an arbitrary website (open/public third‑party content), which the agent must read and interpret to decide which terms/clauses to generate, exposing it to untrusted user-controlled content that could carry indirect prompt injections.