azure-keyvault-secrets-ts
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [Indirect Prompt Injection]: The skill retrieves content from Azure Key Vault, an external data source, which creates a potential surface for indirect prompt injection if the vault contains untrusted or externally influenced content.
- Ingestion points: Secret and key data are ingested into the agent context via
secretClient.getSecretandcryptoClient.decryptinSKILL.md,references/keys.md, andreferences/secrets.md. - Boundary markers: The documentation and code examples do not include explicit boundary markers or instructions to isolate the retrieved content from the agent's reasoning process.
- Capability inventory: The skill provides network access (Azure SDK) and file system write capabilities (backup examples in
references/secrets.md). - Sanitization: No explicit sanitization or validation logic is applied to the retrieved content in the code examples provided.
- [File System Access]: The reference documentation demonstrates how to perform backup and restore operations using the standard
node:fsmodule to interact with the local file system. This is a functional feature for data persistence that requires appropriate environment permissions. - [External Dependencies]: The skill relies on official Azure SDK packages for its core operations. These are standard, versioned dependencies provided by the service vendor for interacting with their cloud platform.
Audit Metadata