azure-keyvault-secrets-ts

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: References official Microsoft Azure SDK packages including @azure/keyvault-secrets, @azure/identity, and @azure/keyvault-keys for installation through the official npm registry. These are verified libraries from a well-known service provider.- [COMMAND_EXECUTION]: Includes standard shell commands for package installation (npm install) and environment variable configuration.- [PROMPT_INJECTION]: Identification of indirect prompt injection attack surface:
  • Ingestion points: Secret values and key properties are retrieved from Azure Key Vault via getSecret and listPropertiesOfSecrets, which injects external data into the agent's context.
  • Boundary markers: The provided instructions do not include explicit delimiters or instructions for the agent to ignore potential instructions embedded within retrieved secret values.
  • Capability inventory: The skill provides capabilities to write secrets (setSecret), create keys (createKey), and perform cryptographic operations (encrypt, sign).
  • Sanitization: The skill does not demonstrate sanitization or validation of the retrieved secret content before it is processed or output to the console.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 08:02 PM
Security Audit — agent-trust-hub — azure-keyvault-secrets-ts