video-storyboard
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from multiple sources to generate storyboards and video scripts.
- Ingestion points: Untrusted data enters the agent context through user prompts, existing video plans, prior conversation history, and character specification files (.md) located in the characters/ directory (SKILL.md).
- Boundary markers: The instructions lack specific requirements for using delimiters or "ignore embedded instructions" warnings when interpolating these external inputs into the prompt for the image generator or the generated markdown script.
- Capability inventory: The skill has the capability to write files to the local file system, specifically creating and saving .png and .md files in the storyboard/ directory (SKILL.md).
- Sanitization: There is no mention of sanitizing, escaping, or validating the content extracted from external plans or character sheets before it is used to influence the agent's output.
Audit Metadata