image-analyzer
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'orth' CLI tool to execute API requests for image processing, text extraction, and screenshot generation as part of its documented workflow.\n- [EXTERNAL_DOWNLOADS]: The skill retrieves image content and website data from external URLs (e.g., example.com, stripe.com) to perform its analysis and scraping functions.\n- [PROMPT_INJECTION]: The skill processes data from external sources (images and web pages) which constitutes an indirect prompt injection surface. Evidence: 1. Ingestion points: 'url', 'website_url', and 'urls' parameters in SKILL.md. 2. Boundary markers: None. 3. Capability inventory: Network requests via 'orth' CLI. 4. Sanitization: None. This risk is inherent to the intended purpose of performing OCR and automated content analysis.
Audit Metadata