visual-image-understanding

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions in SKILL.md include a command to install uv (a fast Python package manager) from astral.sh if it is missing. This is a common developer tool from a recognized provider (Astral). The script also automatically manages the Pillow dependency via uv's inline script metadata.
  • [COMMAND_EXECUTION]: The skill operates by executing a Python script (visual_runtime.py) using uv run. This script performs local image operations (resizing, encoding) and sends requests to an external API.
  • [DATA_EXFILTRATION]: The skill reads local image files, converts them to Base64, and sends them to a remote vision model API endpoint. The endpoint and model are configurable via user-provided environment variables (VISUAL_BASE_URL, VISUAL_MODEL, VISUAL_API_KEY), which is standard for BYO-Key (Bring Your Own Key) utility skills.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes image content which could contain text-based instructions. It acts as an image-to-text bridge. While this presents an attack surface where a malicious image could contain instructions for the agent, the risk is mitigated by the fact that the output is intended to be a descriptive Markdown summary for the user, and the script does not possess capabilities to perform dangerous system actions based on that text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 10:41 AM
Security Audit — agent-trust-hub — visual-image-understanding