to-storyboard
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from SCENES.md and NARRATION.md along with reference documentation to generate a STORYBOARD.md file. This creates an indirect prompt injection surface where instructions embedded in the source markdown files could influence the agent's behavior.\n
- Ingestion points: The agent reads SCENES.md, NARRATION.md, and /hyperframes-core/references/storyboard-format.md (documented in SKILL.md).\n
- Boundary markers: None. The instructions do not specify the use of delimiters or warnings to ignore instructions within the processed data.\n
- Capability inventory: The skill primarily performs local file read and write operations.\n
- Sanitization: None. There is no mention of content filtering or validation for the input files.
Audit Metadata