ln-625-dependencies-auditor

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to fetch mandatory reference files via WebFetch from the public URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path} and to load several "MANDATORY READ" shared/references files, so untrusted third‑party content from that public GitHub location would be read and can materially influence the agent's actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly states that if local shared/ files are missing it will "fetch files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}", and those fetched MANDATORY READ markdown files directly define detection methodology, templates, and worker instructions used at runtime, so this external URL can control prompts/instructions.