visual-audit

Warn

Audited by Snyk on Mar 21, 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's required usage explicitly accepts a URL or screenshot in SKILL.md ("/visual-audit "), so the agent will ingest and interpret arbitrary third-party webpages/images from the open web as part of its workflow, which could carry untrusted/user-generated content able to influence decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 21, 2026, 07:43 AM
Issues
1