ln-910-community-engagement

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory workflow explicitly fetches and reads public GitHub content (e.g., GraphQL queries that pull repository discussions, CHANGELOG.md, and project docs) and also falls back to fetching files via raw.githubusercontent.com, meaning untrusted, user-generated third-party content is ingested and used to drive decisions and delegate actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill will fetch fallback instruction files at runtime from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/{path}, and those raw GitHub files are injected as required shared/reference documents that directly control prompts/instructions.