go-style-guide
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides detailed instructions for auditing Go code based on well-known industry standards. It uses standard command-line tools like grep and ripgrep to identify patterns in source code.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and style guides from established sources such as Google and Uber. These references are used for instructional purposes and do not involve executing untrusted remote code.
- [COMMAND_EXECUTION]: The skill workflow involves using grep and ripgrep via the shell to identify code patterns. These operations are scoped to auditing local source files and do not involve executing untrusted inputs or external scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Go source code, creating a surface for indirect prompt injection. Evidence Chain: (1) Ingestion points: local Go source files and packages; (2) Boundary markers: findings are reported in a structured template; (3) Capability inventory: involves command execution via grep and ripgrep; (4) Sanitization: no explicit sanitization of input source code is described, but the agent's task is limited to an auditing context.
Audit Metadata