review-pull-request

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested when the skill uses an MCP tool to fetch the target PR’s description/body and diff (Step 2 “Identify the Target PR” and Step 3 “Fetch the Code Diff”), which are authored by the PR submitter/other repo contributors rather than the operating user.