onedrive

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the official NPM registry. This is a vendor-owned tool necessary for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands via the membrane CLI to authenticate, manage connections, and interact with the OneDrive API. These commands are integral to the skill's operation and are used according to the vendor's documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides the ability to read and list file content from OneDrive (e.g., via list-folder-contents or get-item-by-path). This allows external, potentially untrusted data to enter the agent's context.
  • Ingestion points: File metadata and content retrieval actions in SKILL.md.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Subprocess execution via membrane action run and membrane request across all integration points.
  • Sanitization: No explicit sanitization or filtering of retrieved file content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 01:36 PM
Security Audit — agent-trust-hub — onedrive