github-copilot-repo-instructions

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

• Third-party content exposure detected (medium risk: 0.65). Outsider-authored free text can enter the LLM context via Copilot Chat/Code Review/Cloud Agent surfaces that this skill configures, because those surfaces ingest user/PR/issue text written by others (e.g., PR body/comments or issue descriptions) alongside the repo’s instruction files.