ln-140-test-docs-creator

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs a fallback WebFetch from the public URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path} to load shared/reference files (e.g., docs_quality_contract.md) which the agent must "MANDATORY READ" and use to drive creation/validation, exposing it to untrusted public GitHub content that can materially influence actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill conditionally performs a runtime WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path} to load templates/references that are then used to drive document generation and content edits, so remote content fetched at runtime can directly control the agent's output.