sdxl
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input (text prompts and reference images) which is then interpolated into API requests sent to the Pixazo gateway.
- Ingestion points: User-provided prompts and reference image URLs/data URLs described in the 'Inputs' section of
SKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to the agent to ignore embedded commands within user input.
- Capability inventory: Performs network POST operations to
gateway.pixazo.aiusingcurl, Pythonrequests, and Node.jsfetch. - Sanitization: No explicit client-side sanitization is defined; the skill relies on the destination API for validation.
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation and permits the installation of additional tools from the vendor's official resources.
- Evidence: Fetches reference schemas from
https://www.pixazo.ai/models/sdxl.md. - Evidence: Provides instructions to install further skills via
npx skills add Pixazo-AI/skills.
Audit Metadata