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 explicitly fetches and ingests open, user-generated GitHub content (Phase 1: "Fetch Data" using gh issue list, gh pr list, and gh api graphql for discussions) and also may WebFetch files from raw.githubusercontent.com, and then reads and interprets those items to classify priorities and drive recommendations, so untrusted third‑party content can materially influence behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly falls back at runtime to WebFetch the file(s) at https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, which will supply required "shared/" Markdown used to drive discovery and classification instructions, so remote content can directly control the agent's prompts/behavior.