The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads and processes project source code and configuration files, creating a vulnerability surface where malicious comments or code patterns could attempt to influence the agent's logic during a modernization scan.
Ingestion points: The skill reads go.mod, .modernize, and all Go source files within the target project codebase.
Capability inventory: The skill is authorized to execute shell commands via Bash (restricted to go, git, and golangci-lint tools), write to the filesystem, and orchestrate sub-agents to perform parallel scans.
Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore embedded natural language instructions within the source code being analyzed.
Sanitization: The skill does not describe any sanitization or validation of content read from source files before it is processed by the LLM.
[COMMAND_EXECUTION]: The skill uses shell commands through restricted tool scopes to manage dependencies, run tests, and handle version control operations.
Evidence: Invokes go mod tidy, go test, go fix, and various git commands to perform modernization workflows.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of official Go development tools and community-recognized libraries.
Evidence: Recommends downloading govulncheck, golangci-lint, and stringer from established community repositories using the standard go get mechanism.

golang-modernize