image-gen

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The script performs network requests to OpenAI's API (api.openai.com) to generate and edit images. This involves sending user-provided prompt text and reference images to the external service.
  • [COMMAND_EXECUTION]: The skill's instructions involve executing a Python script that performs file system writes and network operations.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user input.
  • Ingestion points: The --prompt CLI argument in scripts/image_gen.py accepts arbitrary user-controlled strings.
  • Boundary markers: The prompt is passed directly to the API without delimiters or instructions to ignore embedded commands.
  • Capability inventory: The script has the capability to write files to disk and make network requests.
  • Sanitization: There is no sanitization or validation performed on the prompt input before it is sent to the remote API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 01:22 PM
Security Audit — agent-trust-hub — image-gen