setup-witify-skills

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s required runtime workflow explicitly instructs the agent to “look at the current repo” and “read whatever exists,” including reading issue trackers and related artifacts like existing local-markdown issue files under .scratch/ (user-authored text), which the LLM ingests to summarize findings and proceed.