ln-743-test-infrastructure

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 missing files via WebFetch from the public URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, so the agent will ingest and act on arbitrary public GitHub content that can materially alter scaffolding and tool usage.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly says it will WebFetch templates at runtime from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, meaning external raw GitHub content is fetched and relied upon to drive the skill's scaffolding/instructions and thus can directly control agent behavior.