The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted document formats such as PDF, Word, PowerPoint, and Excel files.
Ingestion points: Untrusted content enters the agent context through file paths processed by the document-converter.py script and subsequently read as markdown.
Boundary markers: No specific delimiters or warnings to ignore embedded instructions within the documents are mentioned in the workflow instructions.
Capability inventory: The skill utilizes local shell execution for Python scripts and performs file system read/write operations for caching purposes at ~/.claude/cache/documents/.
Sanitization: There is no evidence of sanitization, filtering, or escaping of the content extracted from documents before it is presented to the agent as markdown.
[COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Python script ~/.claude/lib/document-converter.py with user-supplied file paths as arguments, which is a standard part of the skill's conversion functionality.

convert-doc