Skills
skills/elizaos/eliza/openai-image-gen/Gen Agent Trust Hub

openai-image-gen

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts/gen.py script downloads generated images from URLs returned by the OpenAI API using urllib.request.urlretrieve.
  • [INDIRECT_PROMPT_INJECTION]: The script is vulnerable to HTML and script injection in the generated gallery file.
  • Ingestion points: The --prompt command-line argument in scripts/gen.py receives untrusted input from the user.
  • Boundary markers: Absent. No delimiters or instructions are used to separate the prompt content from the HTML structure.
  • Capability inventory: The script writes files to the local filesystem (index.html, prompts.json) and performs network operations (OpenAI API requests).
  • Sanitization: Absent. The write_gallery function directly interpolates the prompt variable into the HTML template without escaping or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 06:17 AM