generated-video-quality
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed entirely of markdown instructions for human or AI agent reasoning. It lacks executable scripts (.py, .js, .sh), binary files, or configuration patterns that trigger shell execution.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting project data (e.g.,
SHOTLIST.md,narration-manifest.md, and character reference images) to verify video quality. While these ingestion points could theoretically host malicious instructions, the skill does not possess high-risk capabilities such as network exfiltration or shell access to exploit such content. - Ingestion points:
characters/directory,SHOTLIST.md,narration-manifest.md, andproduction.json(referenced in SKILL.md). - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: No subprocess calls, network operations, or sensitive file system access detected across the instructions.
- Sanitization: Not present; however, the lack of dangerous capabilities mitigates the risk.
Audit Metadata