yapi

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends executing @leeguoo/yapi-mcp via npx. This package is a vendor-owned resource associated with the author's namespace leeguooooo.
  • [COMMAND_EXECUTION]: The skill uses rg (ripgrep) to extract configuration data and executes the yapi CLI tool to perform documentation synchronization and queries.
  • [CREDENTIALS_UNSAFE]: The skill accesses sensitive local files including ~/.yapi/config.toml and ~/.yapi-mcp/auth-*.json. These files are used to store authentication tokens and configurations for the YApi service.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and summarizes external API documentation from a YApi server.
  • Ingestion points: API documentation JSON fetched via the yapi command from a remote base_url (configured in ~/.yapi/config.toml).
  • Boundary markers: The skill does not employ specific boundary markers or instructions to ignore instructions embedded within the fetched documentation during processing.
  • Capability inventory: The skill can execute shell commands (yapi, npx, rg), perform network operations via the YApi CLI, and read/write to specific local directories (~/.yapi).
  • Sanitization: No sanitization of the external JSON documentation is performed prior to summarization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 12:59 AM