golang-pitfalls-code-organization
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes Go source code files and has the authority to edit files and run build/lint commands. This environment is susceptible to indirect prompt injection if the analyzed code contains adversarial instructions designed to influence the agent.
- Ingestion points: Go source code files via paths **/*.go.
- Capability inventory: File system access (Read, Edit, Write, Glob, Grep) and shell command execution via restricted tools (go, golangci-lint, git).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore content within the analyzed files.
- Sanitization: No explicit sanitization or validation of the input source code is defined.
Audit Metadata