landing-page

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow runs scripts/analyze_project.py on a user-supplied project path and reads outsider-authored free text from that project’s README.md and each outsider skill’s SKILL.md (e.g., “What this skill does” / code blocks), which is then printed/serialized and can be inserted into the LLM prompt for README generation.