azure-ai-projects-ts

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified in the evaluation workflows.
  • Ingestion points: Untrusted data is ingested via the evaluationData and datasetId parameters in references/evaluations.md.
  • Boundary markers: The evaluation prompt templates in references/evaluations.md do not utilize delimiters or specific instructions to isolate user-provided content in the {{response}} field.
  • Capability inventory: The client.evaluations.create method (in SKILL.md and references/evaluations.md) allows the agent to execute LLM calls over external data.
  • Sanitization: No sanitization or validation logic is demonstrated for the content being processed.
  • [EXTERNAL_DOWNLOADS]: Fetches configuration and SDK libraries from trusted sources.
  • Evidence: The skill requires the @azure/ai-projects and @azure/identity packages, which are official Microsoft libraries from a well-known service provider.
  • [DATA_EXFILTRATION]: Facilitates access to Azure resource connections and credentials.
  • Evidence: The skill utilizes client.connections.getWithCredentials (in references/connections.md) to retrieve API keys and tokens for linked Azure services, which is its primary intended function for resource integration.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 12:35 AM