image-generator

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided text prompts to generate visual assets, which is a standard surface for indirect prompt injection.
  • Ingestion points: User input flows through the prompt field and the design_config object in the SKILL.md examples.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the user prompt.
  • Capability inventory: The skill utilizes network operations (curl) to send data to an external API endpoint.
  • Sanitization: There is no evidence of sanitization or filtering of the user-provided prompt before it is sent to the backend service.
  • [EXTERNAL_DOWNLOADS]: The documentation references external resources and tools for operation.
  • The skill instructs the use of npx onekey, which involves fetching and executing the onekey package from the npm registry.
  • It utilizes curl to send POST requests to https://agent.deepnlp.org/agent_router, which is the vendor's API gateway.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:06 AM
Security Audit — agent-trust-hub — image-generator