unlimited-ocr-batch-folder

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script (unlimited_ocr_batch_folder_parser.py) using the uv run command to process document folders. This is the primary mechanism for its OCR functionality.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it extracts text from untrusted external sources (PDFs and images).
  • Ingestion points: Untrusted data enters the agent context through the files in the folder path provided to the --folder flag in SKILL.md.
  • Boundary markers: There are no documented boundary markers or system instructions to prevent the agent from obeying instructions found within the parsed document content.
  • Capability inventory: The skill uses Bash, Read, Write, and Glob tools. Malicious instructions in a parsed document could theoretically attempt to exploit these capabilities if the agent processes the OCR output as commands.
  • Sanitization: No sanitization or validation of the extracted OCR text is described, meaning any embedded malicious prompts are passed directly into the output markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 05:05 PM
Security Audit — agent-trust-hub — unlimited-ocr-batch-folder