extracting-with-ocr

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides usage examples for the xberg CLI tool to handle text extraction and OCR backend configuration.
  • [PRIVILEGE_ESCALATION]: The documentation mentions the use of sudo apt install to install Tesseract language packs, which is a standard administrative procedure for managing system dependencies.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes processing text from image-based documents, which creates a surface for potential indirect prompt injection attacks if source files contain hidden instructions.
  • Ingestion points: The xberg extract command processes local user files.
  • Boundary markers: None identified in the instructional examples.
  • Capability inventory: The tool performs file reading and text extraction.
  • Sanitization: No sanitization of the extracted OCR text is described in the documentation.
  • [NO_CODE]: The skill is entirely composed of markdown documentation and does not include any scripts or executable files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 10:22 PM
Security Audit — agent-trust-hub — extracting-with-ocr