vision-framework
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for computer vision tasks that ingest untrusted data, creating a surface for indirect prompt injection.\n
- Ingestion points: Data enters the agent's context through OCR text recognition (
RecognizeTextRequestinreferences/vision-requests.md) and barcode/QR code scanning (DetectBarcodesRequestandDataScannerViewControllerinreferences/visionkit-scanner.md).\n - Boundary markers: The implementation patterns do not include delimiters or specific instructions for the agent to ignore embedded commands within the extracted text or payloads.\n
- Capability inventory: The skill patterns allow for creating
URLobjects from scanned payloads (detectQRCodesinreferences/vision-requests.md), which could lead to unauthorized network requests if an agent follows those links without validation.\n - Sanitization: The provided code snippets lack sanitization or validation of the extracted strings before they are processed or returned.
Audit Metadata