newsletter-visuals
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content (newsletter drafts) to generate prompts for image and voice tools, creating a surface for indirect instructions.
- Ingestion points: The skill reads a newsletter draft in 'Step 1: Audit the Draft' and 'Step 5: Generate Visual Assets' (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or 'ignore instructions' warnings for the interpolated draft content.
- Capability inventory: The skill has the ability to generate images via 'creator-stack:nanobanana' and process text via 'creator-stack:voice'.
- Sanitization: No sanitization or validation of the draft content is performed before it is used to construct prompts for the image generation tool.
Audit Metadata