design-agent

Warn

Audited by Snyk on Apr 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 explicitly uses web-fetching/search tools (e.g., ScrapeWebsiteTool, SerperDevTool and the "Fetch Webpage"/WebFetcherTool examples in references/custom-tools.md) and shows Flows/Agent.kickoff consuming result.raw from those tools for downstream analysis and report-writing, meaning untrusted public web content is fetched and interpreted as part of the agent workflow.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 3, 2026, 07:06 PM
Issues
1