api-designer
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references supporting documentation (e.g.,
domains.md,testmu_example.md) hosted on the LambdaTest GitHub repository. These are documented as external prerequisites for the agent to use when generating API designs. As LambdaTest is a well-known service, these references are categorized as safe. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied descriptions of systems or domains to generate comprehensive API specifications, creating a potential attack surface.
- Ingestion points: User-provided descriptions of API requirements, systems, or domains.
- Boundary markers: Absent; there are no specific delimiters or instructions to treat user-provided descriptions as untrusted data within the prompt template.
- Capability inventory: The skill generates text-based API specifications and contains logic to check for, and potentially invoke, a separate 'API Documentation' skill.
- Sanitization: No validation, escaping, or filtering is performed on the user's input before it is used to generate the API architecture.
- [NO_CODE]: This skill consists entirely of instructional markdown and metadata, without any bundled executable scripts or code files.
Audit Metadata