Skills
Navigate
skills/wvlvik/toy-skills/jimeng-api-image-gen/Gen Agent Trust Hub

jimeng-api-image-gen

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the user that is used to construct API calls and is subsequently reflected in the agent's context.
  • Ingestion points: User-provided prompt and --images URL parameters in scripts/generate_image.py.
  • Boundary markers: None identified in scripts/generate_image.py to separate user content from system instructions.
  • Capability inventory: The skill performs network requests using the requests library and writes generated images to the local filesystem using open().write() in scripts/generate_image.py.
  • Sanitization: The skill enforces a prompt length limit of 800 characters and relies on the remote API's risk filters.
  • [EXTERNAL_DOWNLOADS]: The skill downloads generated image content from visual.volcengineapi.com, which is the official endpoint for a well-known cloud service provider.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 02:51 AM