vsl-storyboard-writer
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as the starting point for a multi-agent pipeline and lacks defensive boundaries for data transmission. \n- Ingestion points: User requirements for scripts are processed through the main skill instructions (SKILL.md). \n- Boundary markers: The storyboard templates (rules/_storyboard-template.md) do not provide delimiters to separate untrusted user data. \n- Capability inventory: While this skill is primarily text-generative, it targets downstream agents (motion-designer) that may have broader system access. \n- Sanitization: There are no explicit instructions to escape or validate external content before inclusion in the 'Motion Designer Notes' used by the next stage of the pipeline.
Audit Metadata