copilot-coding-agent

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly routes GitHub issues (user-written issue bodies) to the Copilot Coding Agent — see "Usage" and "How it works" where labeling an issue triggers Copilot to read the issue text and generate code/PRs — so it ingests untrusted, user-generated third-party content that can directly change agent behavior.