ln-404-test-executor

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 explicitly mandates reading shared/references files and instructs that if local files are missing to fetch them via WebFetch from the public URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, meaning the agent will ingest public GitHub-hosted (untrusted/user-provided) content that can materially influence its actions and decisions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs that if shared/ is missing it will fetch mandatory reference files at runtime via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched docs directly control the agent's required prompts/instructions.