image-tools

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted external content, creating a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent's context through text extracted via OCR using tesseract and content captured from external URLs via chromium or wkhtmltoimage.
  • Boundary markers: No delimiters or safety instructions are defined to help the agent distinguish between data and instructions in the processed output.
  • Capability inventory: The skill utilizes powerful system commands for file manipulation, text extraction, and web rendering.
  • Sanitization: There is no evidence of sanitization or validation logic for the inputs (URLs, filenames) or the outputs (extracted text) within the skill.
  • [COMMAND_EXECUTION]: The skill relies on several system-level utilities including ImageMagick tools (convert, identify), tesseract, and chromium. While the provided examples use shell variable quoting, the execution of these commands with arbitrary user-supplied files or URLs requires robust input management by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:11 AM