azure-ai-vision-imageanalysis-java

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the official Microsoft Azure AI Vision SDK for Java (com.azure:azure-ai-vision-imageanalysis) which is a well-known service.
  • [INDIRECT_PROMPT_INJECTION]: The skill incorporates an attack surface for indirect prompt injection by processing untrusted data from external sources.
  • Ingestion points: External image URLs processed via analyzeFromUrl and text extracted from documents via OCR in SKILL.md.
  • Boundary markers: The provided examples do not use delimiters or specific instructions to isolate extracted text from the agent's logic.
  • Capability inventory: The skill focuses on analysis and console output; it does not contain capabilities for arbitrary command execution or system modification.
  • Sanitization: No sanitization or validation of the text extracted from images is implemented in the provided code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 11:17 AM