go-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external files such as
go.mod, repository scripts, and CI configurations to inform its Go engineering recommendations. This creates a surface for indirect prompt injection if those files contain adversarial instructions. - Ingestion points:
go.mod, repository scripts, CI files, and nearby packages. - Boundary markers: None present; the agent is instructed to read these files directly.
- Capability inventory: General agent capabilities for file reading and command execution are expected to be available.
- Sanitization: No sanitization or validation of the external file content is described.
Audit Metadata