sasjs-adapter
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and usage examples for the
@sasjs/adapterlibrary, which is a legitimate tool for integrating JavaScript/TypeScript applications with SAS backends. All code examples are illustrative and follow standard development practices. - [DATA_EXPOSURE]: The instructions describe the handling of authentication credentials, such as OAuth tokens and login parameters. These are presented as placeholders or configuration requirements for the library's runtime operation; no hardcoded secrets or sensitive credentials are contained within the skill file itself.
- [INDIRECT_PROMPT_INJECTION]: The skill describes a tool that ingests data from external SAS services (via the
request()method). This constitutes a potential surface for indirect prompt injection if the returned data is subsequently processed by an AI agent without sanitization. - Ingestion points: Data enters the agent's context through JSON responses from SAS services retrieved via
sasjs.request(). - Boundary markers: The documentation does not specify the use of delimiters or boundary markers for the data returned from SAS.
- Capability inventory: The library enables network requests to SAS servers, file uploads, and session management.
- Sanitization: The skill documents strict input validation (type checking, length limits) for data sent to SAS, but does not specify sanitization for data received from SAS before it is processed by the agent.
Audit Metadata