write-a-test-plan

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md "Gather external context" step explicitly instructs the agent to fetch user-provided content from external services (Linear, Figma, Notion), which are untrusted, user-generated third-party sources that the agent will read and use to drive its test-plan decisions.