ugc-photo-prompts
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from the media library through the 'get_media' tool to serve as reference points for image generation, which represents an indirect prompt injection surface.
- Ingestion points: External media references are retrieved from the 'get_media' tool (SKILL.md).
- Boundary markers: The skill lacks explicit markers or instructions to ignore commands potentially embedded in the reference media.
- Capability inventory: The skill uses 'generate_image', 'add_clips', and 'insert_clips' to create and position content.
- Sanitization: No sanitization is performed on the retrieved media metadata or content before it is processed by the generation model.
Audit Metadata