The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external data from documents (.docx, .txt). This creates a surface for indirect prompt injection where instructions embedded within a document could attempt to influence the agent's behavior. The skill follows a structured workflow for generating reports which provides context separation.
Ingestion points: Reads file content from user-provided paths (SKILL.md).
Boundary markers: Absent. The instructions do not explicitly define delimiters for the ingested text.
Capability inventory: The skill has access to Read, Grep, Glob, Bash, Write, and Edit tools.
Sanitization: None specified; the agent relies on its internal logic to parse the text.
[COMMAND_EXECUTION]: The skill enables the Bash tool for document operations. The instructions describe legitimate use cases for file processing and do not include dangerous or unauthorized command execution patterns.

wps-proofread