The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/verify.sh script facilitates quality checks using standard Go tools such as go fmt, go vet, and go test, alongside common community linters like staticcheck and golangci-lint. These tools are executed locally to validate code integrity.
[EXTERNAL_DOWNLOADS]: The skill references standard Go libraries and utilities from well-known, trusted sources including golang.org, honnef.co, and official GitHub repositories. These are standard dependencies within the Go ecosystem and do not represent a security risk.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes user-provided Go source code, which serves as a potential vector for indirect prompt injection. Evidence: 1. Ingestion points: User-supplied Go files in the agent's workspace. 2. Boundary markers: Not explicitly defined within the skill's instruction set. 3. Capability inventory: Local shell command execution for code validation and testing via the provided script. 4. Sanitization: The skill recommends security-positive practices including govulncheck for vulnerability detection and strict SQL parametrization.
[SAFE]: The skill content is legitimate and adheres to secure development practices. No evidence of malicious prompt injection, data exfiltration, obfuscation, or persistence mechanisms was found.

go