The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes grep, go, and golangci-lint shell commands to identify and verify linting suppressions. These are standard operations for a static analysis tool operating within a local development environment.
[EXTERNAL_DOWNLOADS]: The skill provides a link to the official documentation for golangci-lint (golangci-lint.run) if the tool is not found. This is a well-known and trusted resource within the Go ecosystem.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It ingests data from //nolint comments and surrounding source code to perform an 'adversarial debate' regarding the necessity of code suppressions.
Ingestion points: The skill captures justification comments and code context from *.go files using grep (as described in SKILL.md).
Boundary markers: There are no specific boundary markers or instructions to ignore embedded commands within the captured code context.
Capability inventory: The skill's capabilities include executing shell commands (grep, go, golangci-lint) and generating code diffs based on analyzed content.
Sanitization: The skill does not implement sanitization or validation of the justification comments before they are interpreted by the LLM.

go-nolint-audit