gpt-image-2

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data (file paths and URLs) and possesses network and file-access capabilities, creating a surface for indirect prompt injection.\n
  • Ingestion points: The script scripts/gpt_image.py accepts local file paths and remote URLs via command-line arguments such as --image, --mask, and --input-image-url.\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are wrapped around the user-supplied inputs before they are incorporated into the API request payload.\n
  • Capability inventory: The skill can read local files (Path.read_bytes), write results to the filesystem (Path.write_bytes), and transmit data over the network (urllib.request.urlopen).\n
  • Sanitization: The tool performs technical validation (size, format, pixel counts) but does not sanitize the contents of input files or metadata for potential malicious instructions intended for the processing LLM.\n- [COMMAND_EXECUTION]: The skill contains logic to execute its own script within its test suite.\n
  • Evidence: The file tests/test_gpt_image.py uses subprocess.run to call scripts/gpt_image.py via the sys.executable interpreter to perform regression testing on CLI arguments. This is a standard and benign development practice.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:09 AM
Security Audit — agent-trust-hub — gpt-image-2