The Agent Skills Directory

[PROMPT_INJECTION]: The 'check' operation reads external content from a target file path provided in the arguments, creating an indirect prompt injection surface. Instructions embedded within a scanned file could attempt to influence the agent's validation logic or report generation.
Ingestion points: Target file content read during the 'check' operation (SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the content being analyzed.
Capability inventory: The skill utilizes Read, Write, Edit, and Bash tools, though no dangerous shell usage is prescribed in the instructions (SKILL.md).
Sanitization: Input content from the target file is not explicitly sanitized before the validation process.

constitution