analyze-and-plan

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow (Step 1 "Visual Analysis") and resources/visual-analysis.md explicitly state the skill may fetch and process "existing URLs" and external websites during analysis, so the agent will read/unpack third‑party web content that can influence generated acceptance criteria and next actions.