virtual-staging

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests external, user-supplied URLs (image_urls) as shown in SKILL.md examples and also documents web_search_query/web_search_citations in references/SSE-EVENTS.md, meaning the agent consumes untrusted public web content that can influence generation tools and subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 07:58 AM