freee-api-skill

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with the freee API to fetch and manage financial and HR data, creating a surface for indirect prompt injection if data retrieved from the API contains malicious instructions. * Ingestion points: Output from the freee_api_get tool, as described in recipes like recipes/deal-operations.md. * Boundary markers: No specific instructions exist to delimit or ignore instructions within the API data. * Capability inventory: The skill provides tools for writing and deleting data (freee_api_post, freee_api_put, freee_api_delete, freee_api_patch, freee_file_upload). * Sanitization: No specific filtering or validation of the API data is mentioned.
  • [EXTERNAL_DOWNLOADS]: The skill guides the user to install a Node.js package from a public registry for configuration. * Evidence: npx freee-mcp configure in SKILL.md. * Source: The package is hosted on npm and is associated with a well-known service provider.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:13 AM
Security Audit — agent-trust-hub — freee-api-skill