paddleocr-ui-test

Warn

Audited by Snyk on Apr 3, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill's main runtime (scripts/ui_test.py) navigates to an arbitrary --url with Playwright, extracts the page DOM via page.evaluate(A11Y_TREE_SCRIPT) and screenshots, and sends that screenshot to a third‑party PaddleOCR/SiliconFlow API (references/ocr-api.md); those untrusted public webpage contents and OCR results are parsed and directly drive test decisions and reports, so third‑party content can materially influence the agent's behavior.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 3, 2026, 08:45 AM
Issues
1