The Agent Skills Directory

[SAFE]: The skill instructions and reference documents consist entirely of Go programming best practices and design patterns. No malicious code, obfuscation, credential harvesting, or unauthorized exfiltration patterns were detected.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and refactor Go source code files, which inherently introduces a surface for indirect prompt injection if the target code contains malicious instructions embedded in comments or strings. This is a standard risk for development-focused skills and is mitigated by the skill's primary focus on type design and linting tools.
Ingestion points: The agent accesses project files matching **/*.go using the Read and Glob tools.
Boundary markers: The skill does not explicitly define delimiters to distinguish code content from instructions, though it focuses on structural elements (structs, interfaces, tags).
Capability inventory: The skill possesses Edit, Write, and Bash capabilities (scoped to go, git, and golangci-lint) to modify and analyze the code.
Sanitization: No specific sanitization or filtering of external code content is defined in the instructions.

golang-structs-interfaces