add-datasource
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined requirements and research findings to generate Go code.
- Ingestion points: User instructions for new datasource types and API discovery results.
- Boundary markers: The instructions do not define specific delimiters for untrusted data during code generation.
- Capability inventory: The skill is designed to write new Go source files to the repository.
- Sanitization: No explicit validation or escaping is specified for user-provided data incorporated into the code.
- [COMMAND_EXECUTION]: The skill instructs the use of local development tools for building and verifying the implementation.
- Evidence: Use of bin/gcx, go test, and mise (a development task runner) to execute build, test, and verification steps.
Audit Metadata