The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes external file data, creating a vulnerability surface for indirect prompt injection. \n- Ingestion points: Document content is ingested using the Glob and Read tools. \n- Boundary markers: The skill does not use specific delimiters or instructions to help the agent distinguish between document text and operational commands. \n- Capability inventory: The skill has access to Write, Edit, and Agent tools, providing the ability to alter files and delegate complex tasks. \n- Sanitization: Input content is not checked for embedded instructions or sanitized before being processed.

translate