setup-sdk-testing

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external and potentially untrusted data from OpenAPI specifications and Arazzo test definitions, creating an indirect prompt injection surface.
  • Ingestion points: The agent processes gen.yaml, OpenAPI specifications, and .speakeasy/tests.arazzo.yaml for configuration and test setup.
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following commands that might be embedded within the processed data files.
  • Capability inventory: The skill utilizes shell commands (speakeasy run, speakeasy test, npm test) and writes to the file system (SDK output and test directories).
  • Sanitization: No mechanisms for sanitizing or filtering the natural language content within the ingested specifications are mentioned.
  • [EXTERNAL_DOWNLOADS]: The documentation provides examples for CI/CD integration that reference a remote resource.
  • Evidence: The GitHub Actions workflow example in SKILL.md references speakeasy-api/sdk-generation-action@v15.
  • Note: This resource belongs to the skill's primary vendor and is used for its intended purpose of automating SDK generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:46 PM
Security Audit — agent-trust-hub — setup-sdk-testing