azure-ai-translation-text-py

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Indirect Prompt Injection Surface: The skill is designed to process and translate text content provided by users or external sources, which is an inherent property of translation tools.
  • Evidence: Methods such as translate, transliterate, and detect in SKILL.md ingest a body parameter containing lists of strings for processing.
  • Context: While this is a standard feature of the SDK, processing untrusted data can occasionally influence downstream agent logic if the resulting translations are used without proper validation or sanitization.
  • External Package Installation: The skill requires the installation of a specific library to interact with the translation service.
  • Evidence: pip install azure-ai-translation-text in SKILL.md.
  • Context: This is a standard installation of the official SDK library associated with the skill's author.
  • Network Communication with Service Endpoints: The skill establishes connections to cloud infrastructure for processing translation and language detection requests.
  • Evidence: References to cognitiveservices.azure.com and microsofttranslator.com in SKILL.md.
  • Context: These are official service endpoints for Azure AI Translator, which are necessary for the skill to function as intended.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:51 PM
Security Audit — agent-trust-hub — azure-ai-translation-text-py