scenario-image-editing
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the installation of additional skills from the vendor using the npx command with the scenario-labs/skills identifier. This is a standard practice for managing extensions within the platform.
- [COMMAND_EXECUTION]: The instructions direct the agent to prompt the user to execute installation commands for missing dependencies, maintaining human-in-the-loop oversight.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted images and generative text prompts. While no explicit sanitization is documented, the capability is limited to image generation models, which is the primary and intended purpose of the skill.
Audit Metadata