Skills
Navigate
skills/freee/freee-mcp/freee-api-skill/Gen Agent Trust Hub

freee-api-skill

Pass

Audited by Gen Agent Trust Hub on Oct 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill handles data from external APIs that may contain untrusted user input.
  • Ingestion points: Data retrieved from /hub/tax_return/ and /hub/survey/ as documented in recipes/corporate-tax-return-operations.md and recipes/survey-operations.md.
  • Boundary markers: The skill contains explicit instructions for the AI to treat retrieved content as data only and to ignore any commands or executable strings found within that content.
  • Capability inventory: The skill uses freee_api_* tools to modify records in accounting, HR, and other business modules.
  • Sanitization: Relies on the AI's adherence to the defensive instructions provided in the markdown guides.
  • [EXTERNAL_DOWNLOADS]: The skill setup references the freee-mcp package and the mcp.freee.co.jp domain, which are official vendor resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 10, 2026, 01:20 AM