ln-113-backend-docs-creator

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

• Third-party content exposure detected (high risk: 0.70). This skill's SKILL.md explicitly instructs that if the local shared/ directory is missing it will fetch required reference files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path} and also mandates reading shared/references/* files (MANDATORY READ), so public GitHub-hosted content would be ingested and could materially influence document generation and validation.

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 WebFetch at runtime from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path} to load "shared/references" templates and contracts that are marked MANDATORY READ and therefore can directly control prompt/instruction behavior.