cinematic-drama-scene
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows secure prompt engineering practices by requiring the agent to ground its output in specific, provided evidence rather than inventing new content. It includes explicit safety and attribution rules that prevent the impersonation of creators or the unauthorized use of private assets.
- [INDIRECT_PROMPT_INJECTION]: The workflow ingests content from
references/cases.md. This represents a potential indirect injection surface; however, the data is bundled within the skill package, and the 'Required evidence gate' instructions include a 'Preserve / Replace / Avoid' logic that serves as a sanitization step for the generated output. - [EXTERNAL_DOWNLOADS]: The skill contains references to external video and image assets hosted on GoodCase, X (formerly Twitter), and WeChat. These links are provided for stylistic reference and are consistent with the skill's primary purpose of cinematic storyboarding.
Audit Metadata