qa

Warn

Audited by Snyk on Nov 18, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The required browser QA workflow navigates to a user-selected or discovered target URL and reads its page text, DOM, and console output (sections/qa-patterns.md Phase 3 innerText extraction), and the test-bootstrap path runs web searches for test-framework comparisons; outsider text is only reached after the agent chooses a page or query, so this is low.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 18, 2026, 11:46 AM
Issues
1