The Agent Skills Directory

[COMMAND_EXECUTION] (LOW): The skill executes cat, grep, and head to inspect source files. These are standard tools for code auditing and are used within the scope of the skill's stated purpose.
[PROMPT_INJECTION] (LOW): The skill reads external data from the filesystem which could contain malicious instructions.
Ingestion points: Reads file contents from internal/theme/theme.go and the internal/app/ directory.
Boundary markers: No delimiters or instructions are used to separate file content from agent instructions.
Capability inventory: The skill can execute shell commands via the ! prefix.
Sanitization: There is no filtering or sanitization of the content read from the files.

theme-audit