ln-912-community-announcer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public GitHub content (e.g., fallback WebFetch from raw.githubusercontent.com and the Phase 2 step to "check the last 3 announcements in Discussions") and mandates reading those user-generated Discussion posts and remote files as part of style selection and composition, so untrusted third-party content can materially influence its actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly falls back at runtime to fetching required templates and checklists from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched files (style templates, humanizer checklist, discovery docs) directly control prompt/content generation and are required for the skill to run.