The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from a project's codebase, including source files and configuration files like go.mod. This creates a theoretical surface for indirect prompt injection where malicious instructions could be embedded in the code being analyzed. However, this is the primary and intended function of the skill.
Ingestion points: Project Go source files, go.mod, go.work, and .modernize files.
Boundary markers: None explicitly defined; the skill performs standard static analysis of the provided context.
Capability inventory: The skill can suggest code modifications and execute standard Go development tools (go, golangci-lint, govulncheck).
Sanitization: None; the skill provides modernization suggestions based on the raw content of the repository.
[COMMAND_EXECUTION]: The skill utilizes standard Go development commands such as go mod, go get, and go tool. These are expected behaviors for a tool assisting with Go language upgrades and project maintenance.
[EXTERNAL_DOWNLOADS]: The skill references official Go documentation and security tools. All URLs point to trusted domains including go.dev and vuln.go.dev. These resources are provided by the official Go team at Google.

golang-modernize