framework-critical-thinking

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

• Third-party content exposure detected (high risk: 0.80). The skill's self_verification component (references/self_verification.md) explicitly instructs using "web_search" and external knowledge bases for cross-verification and factual checks (and lists public URLs as sources), which means the agent is expected to fetch and interpret open/public third‑party content.