changelog

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated content from third-party services — GitHub PRs via gh search prs and Linear tickets via the Linear MCP tools — (see "Data sources" / "Fetch PRs" and "Fetch Linear tickets" in SKILL.md), and the agent is expected to read and interpret PR bodies, titles, branch names and ticket content to classify, cross-reference, and decide how to render/merge items, so untrusted content could materially influence behavior.