ln-810-performance-optimizer

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md mandates reading shared/reference files and explicitly instructs a WebFetch fallback to fetch files from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, meaning the agent will fetch and interpret public GitHub raw content (untrusted third‑party) as part of its required runtime contract and decision-making.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly says that if shared/ is missing it must fetch mandatory "shared/references" runtime contract and protocol files at runtime from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched documents are required reads that directly determine the agent's instructions/behavior.