design-agent

Warn

Audited by Snyk on May 5, 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 instructs agents to use web-search and scraping tools (e.g., SerperDevTool, ScrapeWebsiteTool in SKILL.md Agent.kickoff examples) and includes custom tool examples that fetch arbitrary URLs (references/custom-tools.md fetch_webpage and WebFetcherTool), so agents will ingest untrusted public web content which can influence their planning and actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 5, 2026, 10:33 AM
Issues
1