reply-to-pr-conversation

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly requires using the "processed-item" list containing each item's "original comment body" from PR issue comments (GitHub user-generated content) and instructs the agent to read, quote, and act on that content when drafting and posting replies, so untrusted third-party comments could influence behavior.