editorial-portrait-composition

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow reads references/cases.md on every invocation and ingests the case cards’ free-text prompt excerpts/summaries (including links like original sources), which are outsider-authored content within the file being read.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The Skill requires inspecting anchor Cases listed in references/cases.md and those Case entries contain external media/evidence links (e.g., https://cms-assets.youmind.com/media/1785143493732_xu4dij_HOKmtpTaYAAP1_0.jpg and https://goodcase.ai/cases/3d-cg-c35a17fc041c) that the agent would fetch at runtime and use to directly inform prompts, so this is a runtime external dependency controlling prompt content.