microsoft-outlook
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
@membranehq/clipackage via npm. This is a vendor-owned resource for managing communication with the Membrane platform.- [COMMAND_EXECUTION]: The instructions involve running variousmembraneCLI commands to handle authentication, manage app connections, and execute API actions.- [INDIRECT_PROMPT_INJECTION]: - Ingestion points: Data from Microsoft Outlook is ingested via
membrane action runandmembrane requestcommands (documented in SKILL.md). - Boundary markers: The instructions do not specify explicit delimiters for untrusted data, though the use of machine-readable JSON is encouraged.
- Capability inventory: The agent has the capability to execute CLI commands and perform network operations through the Membrane proxy.
- Sanitization: The skill recommends using pre-built actions which handle common edge cases, but does not detail specific sanitization for arbitrary external content.
Audit Metadata