microsoft-graph-api

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements patterns for ingesting data from external API endpoints (Microsoft Graph), which represents a potential surface for indirect prompt injection if the returned data (emails, calendar events, etc.) contains malicious instructions.
  • Ingestion points: API responses fetched in graphRequest, graphFetchAll, and graphBatch within SKILL.md.
  • Boundary markers: Not explicitly defined in the provided code templates.
  • Capability inventory: The skill facilitates network requests to Microsoft Graph endpoints and processes JSON payloads.
  • Sanitization: The provided helper functions do not implement explicit sanitization of the returned JSON data before it would be passed to an agent context.
  • [EXTERNAL_DOWNLOADS]: The skill references official Microsoft SDKs and documentation, which are considered well-known and trusted sources.
  • Trusted references: graph.microsoft.com, learn.microsoft.com, and official SDK packages like @microsoft/microsoft-graph-client and msgraph-sdk-python.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:54 AM