paper-illustration
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text and photo descriptions to generate prompts for downstream image generation models.
- Ingestion points: User-supplied text to be included in the illustration and descriptions of photos provided in SKILL.md.
- Boundary markers: The skill uses a strict template and verbatim output instructions to encapsulate the user-supplied content.
- Capability inventory: The skill produces text output only and lacks capabilities for file system access, network operations, or command execution.
- Sanitization: The skill does not perform explicit sanitization, validation, or filtering of the user-provided text strings.
Audit Metadata