start-new-sdk-project

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill instructs the agent to use the speakeasy CLI for SDK generation. The command parameters are limited to the tool's intended functionality.
  • [CREDENTIALS_UNSAFE] (SAFE): The documentation correctly advises using environment variables (SPEAKEASY_API_KEY) or interactive login rather than hardcoding API keys.
  • [PROMPT_INJECTION] (SAFE): No malicious instructions or attempts to bypass agent safety filters were detected in the skill content.
  • [DATA_EXFILTRATION] (SAFE): While the skill can fetch schemas from remote URLs, this is a standard feature of the tool, and no unauthorized data transmission patterns were found.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill ingests external data (OpenAPI specs). While this is an inherent attack surface for SDK generation tools, the skill provides clear boundaries for its operation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:13 PM