batch-linear-tickets

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 consumes user-generated Linear ticket data (see Step 1a: "Fetch each ticket's labels via mcp__claude_ai_Linear__get_issue") and then uses the investigator's Evidence Record and the Feature/Bug packs (which include "Sources" like ticket text, attached design docs, and user-supplied files) to drive classification, planning, and automated PR execution, so untrusted third‑party ticket/content can materially influence agent actions.