screen-reader-testing
Warn
Audited by Snyk on Jul 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s required workflow is “manual screen reader testing” of a page using real assistive tech (e.g., NVDA/JAWS/VoiceOver/TalkBack), which at runtime causes the LLM context to ingest the page’s rendered text/DOM content that is authored by outsiders (the target website/page content), creating indirect prompt-injection exposure via that page text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata