The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external file content via tools like file_outline, read_symbol, and repo_map, which serves as an ingestion point for untrusted data. There are no explicit boundary markers or sanitization steps mentioned to prevent the agent from potentially following instructions embedded within the files it reads. However, this functionality is the primary purpose of the skill and is standard for code analysis tools.
Ingestion points: File reading tools (file_outline, read_symbol, repo_map, find_references).
Boundary markers: Absent.
Capability inventory: Reading local file outlines, symbol definitions, and repository structures.
Sanitization: Absent.
[COMMAND_EXECUTION]: The setup instructions involve standard build commands (go test and go build) to be executed by the user to prepare the environment. These are routine development operations and do not represent a security risk within the skill's operational context.

context