ln-910-community-engagement

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly loads and parses project-local and public GitHub content—e.g., mandatory reads like shared/references/community_github_discovery.md, docs/community_engagement_strategy.md in the target repo, GraphQL queries that fetch Discussions and CHANGELOG.md, and a WebFetch fallback to raw.githubusercontent.com—so it ingests untrusted, user-generated third‑party content and uses it to decide and delegate actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs at runtime to fetch fallback instruction files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched markdown files (strategy/protocol templates) directly control agent behavior and prompts if local copies are missing.