github-star-manager

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and ingests public, user-generated content (e.g., arbitrary webpages via the SKILL.md "内容提取与上下文分析" WebFetch flow and GitHub data via star_tracker.py's get_readme, get_starred_repos, get_latest_release) and then directly acts on that input (e.g., auto-searching/gh-starring repos and passing READMEs into AI summarization in summarize_with_ai), so untrusted third-party content can materially influence tool actions.