ln-654-resource-lifecycle-auditor

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs (in SKILL.md) to fetch missing shared/ reference files via WebFetch from the public URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, meaning it ingests public GitHub content (untrusted third-party data) that the agent must read and that can materially influence its audit logic and outputs.

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 WebFetch missing shared files from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those "MANDATORY READ" documents would be fetched and directly control the auditor's instructions/behavior, making this a required runtime dependency.