BrightData
Warn
Audited by Snyk on Mar 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: 1.00). The skill's SKILL.md and Workflows/FourTierScrape.md explicitly instruct the agent to fetch and extract content from arbitrary user-provided URLs using WebFetch, curl, Playwright, or Bright Data MCP, thereby ingesting untrusted public web content (user-generated/third-party sites) that the agent will read and return—exposing it to potential indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill fetches arbitrary user-supplied URLs at runtime (e.g., https://example.com) via WebFetch / curl / Playwright / Bright Data and injects the retrieved page content into the agent context (convert-to-markdown), which can enable remote prompt-injection from that URL's content.
Audit Metadata