inkos-play-illustration
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external narrative descriptions and world rules, creating a potential surface for indirect prompt injection attacks.\n
- Ingestion points: The skill body explicitly mentions using "supplied narration and world rules" as reference material for generation.\n
- Boundary markers: The instructions lack explicit delimiters or specific directives to the AI to ignore instructions embedded within the narrative content.\n
- Capability inventory: The skill is restricted to providing visual instructions for image generation; it does not request or use any tools, network operations, or file system access.\n
- Sanitization: No methods for filtering, escaping, or validating the external narrative content are provided.
Audit Metadata