The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as chat logs, old documents, and spoken descriptions which could contain hidden instructions designed to influence the agent's output.
Ingestion points: User-provided descriptions, chat logs, and legacy documents are processed as the primary source material in the Workflow section.
Boundary markers: The instructions do not define clear delimiters or use "ignore embedded instructions" warnings for the external content being processed.
Capability inventory: The skill leverages internal tools to generate and deliver Microsoft Word documents based on the processed content.
Sanitization: There are no instructions for the agent to sanitize or filter potential instructional content found within the user-provided source materials before document generation.

sop-writer