api-designer
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow involves executing command-line utilities to validate and mock API specifications. These tools are industry standard for API development tasks.
- Evidence: Mentions of
npx @redocly/cli lint openapi.yamlandnpx @stoplight/prism-cli mock openapi.yamlin the core workflow (SKILL.md). - Evidence: Mentions of
openapi-generator-cli,swagger-cli, andspectralfor validation and code generation (references/openapi.md). - [EXTERNAL_DOWNLOADS]: The use of
npxto run validation and mocking tools involves fetching the respective packages from the public npm registry if not locally available. - Evidence: Use of
npxfor developer tools provided by well-known services like Redocly and Stoplight (SKILL.md). - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided API specifications and possesses the capability to run tools on that data, creating a potential surface for indirect prompt injection through malicious specification files.
- Ingestion points: API specification files such as
openapi.yaml(SKILL.md). - Boundary markers: The skill does not explicitly instruct the agent to use boundary markers when processing external data.
- Capability inventory: Shell command execution capabilities are present through the suggested linting and mocking tools (SKILL.md, references/openapi.md).
- Sanitization: Input content is processed by CLI tools without specific sanitization instructions defined in the skill.
Audit Metadata