go-uber-style-guide
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process and refactor Go code provided by users, which could contain malicious instructions embedded in comments or logic to influence agent behavior.\n
- Ingestion points: Go source files provided by the user for review or refactoring (SKILL.md, references/style.md).\n
- Boundary markers: None specified in the instructions; relies on the agent's internal safety mechanisms.\n
- Capability inventory: The skill demonstrates and encourages file system operations (os.WriteFile, os.ReadFile) and execution of development tools (SKILL.md, references/style.md).\n
- Sanitization: The instructions do not include steps to sanitize or strip potentially malicious prompt fragments from the input code.\n- [EXTERNAL_DOWNLOADS]: The skill references several well-known and trusted Go community libraries and tools for code quality and safety.\n
- Evidence: Mentions
go.uber.org/atomic,go.uber.org/goleak,golangci-lint,revive,errcheck, andstaticcheck(SKILL.md, references/style.md, assets/.golangci.yml).\n - Context: These are standard industry tools for Go development and are referenced here for legitimate instructional and configuration purposes.
Audit Metadata