photo-realism
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied rough ideas or existing prompts and interpolates them into a structured prompt template.
- Ingestion points: User input for the image subject, garments, or faces is parsed in SKILL.md and used to generate the final output.
- Boundary markers: The prompt template uses bracketed placeholders but lacks explicit instructions to the agent to ignore or sanitize embedded instructions within the user-provided data.
- Capability inventory: The skill utilizes Read, Write, and Edit tools in SKILL.md, allowing it to perform file operations based on processed input.
- Sanitization: No input validation or escaping of user-provided content is performed before it is included in the prompt generation process.
- [NO_CODE]: The skill consists exclusively of instructional content in SKILL.md and does not include any executable scripts or binaries.
Audit Metadata