The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to audit and write Go source code, creating a surface for indirect prompt injection where malicious instructions could be embedded in code comments or strings of the files being processed.
Ingestion points: The skill targeting includes all Go source files (**/*.go) as defined in the paths frontmatter.
Boundary markers: The instructions do not define specific delimiters or "ignore" directives to prevent the agent from accidentally following instructions contained within the code it analyzes.
Capability inventory: The skill has access to powerful tools including file system modification (Edit, Write) and shell command execution (Bash scoped to go, git, and golangci-lint) through its allowed-tools configuration.
Sanitization: There is no mention of sanitizing, escaping, or validating the content of the Go files before the agent processes them.

golang-code-style