image-prompts
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are limited to natural language processing and formatting of image prompts. No execution of arbitrary code, network exfiltration, or persistence mechanisms were found.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied visual briefs and references to generate prompts. While these are external inputs, the skill's output is primarily natural language text intended for image generators, presenting minimal risk to the agent environment.
Audit Metadata