web-perf

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends that users configure their environment using npx -y chrome-devtools-mcp@latest. This command downloads and executes the latest version of the Chrome DevTools MCP server from the NPM registry, a well-known package repository.
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze data from external websites, which presents a surface for indirect prompt injection attacks.
  • Ingestion points: Untrusted data enters the agent context through target URLs processed via navigate_page, list_network_requests, and take_snapshot (accessibility tree).
  • Boundary markers: The instructions do not currently define explicit boundary markers or 'ignore' directives to prevent the agent from following instructions potentially embedded in the analyzed web content.
  • Capability inventory: The skill uses tools for browser navigation, performance profiling, network request inspection, and accessibility analysis.
  • Sanitization: There is no evidence of sanitization or filtering applied to the data retrieved from external URLs before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 10:50 AM
Security Audit — agent-trust-hub — web-perf