project-init

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md shows the skill explicitly uses GitHub commands (e.g., "gh repo list", "gh project list", "gh label list") and reads/appends a CLAUDE.md config block in repositories as part of its required workflow, so it ingests user-generated GitHub content (potentially public/untrusted) that can change agent behavior and routing.