Skills
Navigate
skills/prunaai/pruna-skills/p-image-try-on/Gen Agent Trust Hub

p-image-try-on

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied image URLs and optional prompt text to generate new image content.
  • Ingestion points: The person_image, garment_images, and prompt fields are used as inputs for image generation predictions as described in SKILL.md.
  • Boundary markers: There are no specific instructions to use delimiters or ignore embedded instructions within the provided images or prompts.
  • Capability inventory: The skill performs network HTTP requests to the vendor's API (api.pruna.ai) for file uploads and prediction generation.
  • Sanitization: The skill does not describe explicit sanitization, filtering, or validation steps for the external image data or prompt strings before they are sent to the AI model.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install prerequisite and related skills from the PrunaAI/pruna-skills GitHub repository using the npx skills add command.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 11:10 PM