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
bodyparameter in thetranslate,transliterate,detect,lookup_dictionary_entries,lookup_dictionary_examples, andfind_sentence_boundariesmethods as documented inSKILL.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