azure-ai-translation-text-py

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface through its core text processing capabilities.\n
  • Ingestion points: Untrusted data enters the agent context through the body parameter in the translate, transliterate, detect, lookup_dictionary_entries, lookup_dictionary_examples, and find_sentence_boundaries methods as documented in SKILL.md.\n
  • Boundary markers: The implementation examples do not utilize delimiters or explicit instructions to ignore embedded commands within the processed text strings.\n
  • Capability inventory: The skill allows the agent to perform network requests to Azure AI service endpoints (*.cognitiveservices.azure.com) and ingest the results back into the session.\n
  • Sanitization: There is no evidence of input validation or sanitization of the strings passed to the translation API within the provided code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 12:34 AM