gemini-vision

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface\n
  • Ingestion points: The scripts scripts/analyze-image.py and scripts/upload-file.py ingest data from local file paths and user-provided URLs.\n
  • Boundary markers: The prompt and image data are sent as distinct parts to the Gemini API; however, the skill lacks explicit delimiters or instructions to the model to ignore embedded commands within images or documents (e.g., OCR-based injections in PDFs).\n
  • Capability inventory: The skill allows file reading (open), network downloads (requests.get), and communication with external Google APIs via the google-genai SDK.\n
  • Sanitization: Validation is limited to file existence checks and MIME type identification based on file extensions.\n- [EXTERNAL_DOWNLOADS]: The scripts/analyze-image.py script uses the requests library to download content from arbitrary URLs provided as arguments, which could lead to server-side request forgery (SSRF) or processing of malicious content if used with untrusted links.\n- [COMMAND_EXECUTION]: The skill requires the execution of Python scripts (analyze-image.py, upload-file.py, manage-files.py) that perform local file system operations and external network requests to Google services.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 06:30 PM