skill-optimizer

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs using Skill_Seekers and provided scripts (see SKILL.md "Populating References from Documentation (Optional)", scripts/scrape_documentation_helper.py, and references/documentation-scraping.md) to scrape public websites, GitHub repos, and arbitrary documentation URLs into the skill's references, which Claude then reads and uses to inform decisions and actions—exposing the agent to untrusted third-party content that can materially influence behavior.