tech-manga-explainer

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). Two personal GitHub repositories are referenced as installation sources for an unvetted plugin/skill (used to deliver Python scripts/plugins), which can be used to distribute untrusted or malicious code — other URLs are official and low-risk.

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

• Third-party content exposure detected (high risk: 0.75). In the required runtime workflow, the user-supplied free-form fields --prompt and --dialogue are interpolated into the generated LLM image prompt (scene/dialogue sections) in scripts/generate_tech_manga.py, so any outsider-authored text the operating user passes through those arguments would enter the LLM context via --prompt full_prompt to nanobanana-skill.