azure-storage-file-share-ts

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • Official SDK Integration: The skill installs and uses @azure/storage-file-share and @azure/identity via standard package managers. These resources originate from a well-known service provider and are intended for the skill's primary purpose.
  • Credential Security Practices: The documentation encourages using environment variables and DefaultAzureCredential rather than hardcoding sensitive information like account keys or connection strings. This is a recommended practice for secure application development.
  • Local File System Access: Several operations involving fs access the local file system to facilitate uploads and downloads. Users should be aware of the file paths being accessed by the agent.
  • Indirect Prompt Injection Surface: The skill is capable of reading data from external sources, which presents a potential area for review regarding indirect prompt injection. (1) Ingestion points: Data enters the context through file download operations. (2) Boundary markers: The examples do not specify delimiters to separate untrusted file content from agent instructions. (3) Capability inventory: The skill possesses capabilities for network requests (Azure API), file system writes, and package installation. (4) Sanitization: No explicit sanitization of downloaded content is performed before it is processed by the agent. This represents a surface where external data could influence agent responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:52 PM
Security Audit — agent-trust-hub — azure-storage-file-share-ts