ce-plan

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly instructs the agent to perform external research and "retrieve current sources" (see SKILL.md Phase 2 "Run external research" and the Constraints line "for time-sensitive or external claims, retrieve current sources first and cite explicit dates"), and its templates/examples include public URLs (e.g., https://linear.app/developers/graphql), so the agent is required to fetch and interpret untrusted third‑party web content which can materially affect planning decisions.