ocr
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: Executes a local Python script
pipeline.pyvia a Bash command within a virtual environment. This script is used to process images in a specific directory and output results to a text file. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (screenshots from the
output/captures/directory). - Ingestion points: Image files located in
output/captures/. - Boundary markers: None specified; the skill directly extracts and displays text to the user.
- Capability inventory: Executes shell commands via
Bashand reads local files. - Sanitization: No evidence of sanitization or filtering of the OCR-extracted text before it is presented to the user or processed further.
Audit Metadata