The Agent Skills Directory

[PROMPT_INJECTION]: The skill operates on file content provided by the user to perform iterative optimization, which creates a surface for indirect prompt injection.
Ingestion points: Processes content from a file path identified via $ARGUMENTS or user query.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the files it optimizes.
Capability inventory: The skill has the ability to write to the file system (both temporary and original paths) and chain other agent skills.
Sanitization: No sanitization or validation of the file's content is described before it is processed by the engineering tools.

auto-optimize-prompt