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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata