The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of external, untrusted documents (PDF, DOCX, XLSX) which may contain malicious instructions designed to influence the agent's behavior once extracted.
Ingestion points: local files passed to the xberg batch command or extract_batch API.
Boundary markers: None explicitly defined in the skill documentation.
Capability inventory: The skill enables bulk file reading, content extraction, and structured data generation.
Sanitization: The skill does not describe any specific sanitization or filtering of the extracted content before it is returned to the agent.
[COMMAND_EXECUTION]: The skill documentation provides examples of shelling out to local CLI tools.
Evidence: Examples include the use of xberg batch, jq, find, and mkdir commands to manage files and process extraction results.

batch-extraction