msgraph-files

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and executes the @anthropic-ai/microsoft-graph-mcp package via npx. This package is maintained by a trusted organization.
  • [COMMAND_EXECUTION]: Executes shell commands via a helper script to interact with the Microsoft Graph API, which is necessary for the skill's file management capabilities.
  • [PROMPT_INJECTION]: The graph_get_file_content tool retrieves data from remote documents, creating a potential surface for indirect instructions.
  • Ingestion points: graph_get_file_content in SKILL.md reads content from remote storage items.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are present in the tool definition.
  • Capability inventory: Includes file uploads and directory management via npx.
  • Sanitization: Content is ingested directly into the agent context without specialized filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 06:12 AM