github-to-skill

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

• Third-party content exposure detected (high risk: 0.90). This skill searches and fetches content from public GitHub repositories (via scripts like scripts/search_github_repos.py and scripts/generate_skill_template.py) and then analyzes repository docs/structure, which are arbitrary user-generated, untrusted third-party content the agent will read and interpret.