presentations

Warn

Audited by Snyk on Mar 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.md explicitly requires the agent to perform batch web searches (image-search, web-search), "scrape key pages for detail" via scrape-webpage, and download images from arbitrary URLs (curl in Phase 3), so the agent ingests and acts on untrusted public web content that can materially influence design and subsequent tool actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 08:35 AM