setup-sdk-testing
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
speakeasy test,speakeasy run, and language-specific test runners likenpm testorpytest. These commands are essential for the primary purpose of generating and validating SDKs. - [EXTERNAL_DOWNLOADS]: The skill references official vendor resources, including the
speakeasy-api/sdk-generation-actionGitHub Action and instructions for updating the Speakeasy CLI, which are expected components of the development workflow. - [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface where untrusted data from external files is processed to influence agent behavior or code generation.
- Ingestion points: Processes user-provided OpenAPI specifications,
gen.yamlconfigurations, and.speakeasy/tests.arazzo.yamlworkflow definitions. - Boundary markers: The instructions do not specify the use of delimiters or specific warnings to the agent to ignore potentially malicious instructions embedded within the API specifications or test definitions.
- Capability inventory: Includes the ability to write files (generated tests), perform network operations (executing API calls during integration or Arazzo tests), and execute subprocesses through the CLI tools.
- Sanitization: There is no mention of sanitization or strict schema validation of the external specification content before it is processed by the generation and testing tools.
Audit Metadata