setup-skill-discovery

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

• Third-party content exposure detected (medium risk: 0.65). Yes—Step 1 reads repo files like README.md and CLAUDE.md (outsider-authored free text from the project’s repository) and Step 3/4 then uses that content for LLM reasoning and to generate the YAML that later drives LLM injection.