go-test-engineering
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on Go source code and test files within a workspace, which serves as a potential untrusted data ingestion point where malicious instructions could be embedded in code or comments.
- Ingestion points: All Go source files (.go) and test files (*_test.go) in the repository (SKILL.md).
- Boundary markers: The instructions do not define delimiters or explicit warnings to ignore instructions found within analyzed code.
- Capability inventory: The agent is authorized to modify repository files and execute local commands including
go testandmake(SKILL.md). - Sanitization: No sanitization or escaping of repository content is prescribed before it is processed by the agent.
Audit Metadata