walkthrough-process

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly says in "Optional Linear workflow (branch mode only)" that if the user provides an issue id or URL the agent will "fetch and use it as intent context," meaning it ingests user-generated third-party content from Linear issues which can influence its walkthrough decisions.