papercraft-stop-motion-explainer
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided topics and source material to generate production plans and prompts, creating a potential surface for indirect prompt injection.
- Ingestion points: Topic, knowledge points, or source material provided by the user (SKILL.md, Step 1).
- Boundary markers: There are no explicit delimiters or "ignore embedded instructions" warnings defined in the prompting steps for user input.
- Capability inventory: The skill writes multi-section production documents to the canvas, generates prompts for image and video models (MiniMax-H3), and involves audio generation and quality verification (SKILL.md, Steps 8-12, 17).
- Sanitization: Instructions explicitly state to "Preserve the user's domain words and do not simplify the science," which discourages the sanitization or filtering of the source content (SKILL.md, Step 1).
Audit Metadata