ln-911-github-triager

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

• Third-party content exposure detected (high risk: 1.00). The skill's Phase 1 "Fetch Data" steps explicitly run gh commands and a GraphQL query to load open GitHub issues, pull requests, and discussions (public, user-generated content) which the agent then reads and interprets in Phases 2–5 to classify items and drive triage actions, exposing it to untrusted third-party content from GitHub.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill will at runtime fetch required shared files via https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and that externally fetched content directly influences the agent's discovery and triage logic (controlling prompts/instructions), making it a required runtime dependency.