ln-743-test-infrastructure

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to fetch missing shared files via WebFetch from the public URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, which causes the agent to ingest and act on public GitHub content (untrusted third‑party material) as part of its workflow.

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

• Potentially malicious external URL detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to WebFetch runtime files from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, which would fetch remote code/templates (e.g., test fixtures/configs) that can be written into the project and later executed by test runs, so this is a runtime fetch of executable remote content the skill may rely on.