higress-daily-report

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly fetches and ingests public, user-generated GitHub issues/PRs from the alibaba/higress repository using gh commands (e.g., "gh search issues", "gh issue view" and comment/view workflows) and then reads titles/bodies/comments to classify issues, generate replies, update tracking state, and post follow-up actions, so untrusted third-party content can directly influence agent decisions and tool use.