openai-image-gen

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads images from OpenAI's API and the temporary URLs generated during the process. These are expected behaviors for the skill's stated purpose and target well-known services.
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute a Python script and use shell commands to view generated output locally.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection within the generated HTML gallery.
  • Ingestion points: Image prompt text provided via CLI arguments in scripts/gen.py.
  • Boundary markers: None; prompt text is directly embedded in HTML.
  • Capability inventory: File-system write operations and network requests for image retrieval.
  • Sanitization: The script lacks HTML escaping for prompt strings before they are written to the gallery file.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:20 PM