skills/midudev/autoskills/web-perf/Gen Agent Trust Hub

web-perf

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests and analyzes untrusted data from external websites.
  • Ingestion points: Target website content and network data accessed via navigate_page and list_network_requests tools.
  • Boundary markers: The instructions do not define specific delimiters or security headers to isolate external data from agent instructions.
  • Capability inventory: The skill utilizes the chrome-devtools MCP tools for navigation, tracing, and network analysis. It does not possess arbitrary code execution or file writing capabilities.
  • Sanitization: No explicit sanitization or validation of the external web data is implemented in the skill instructions.
  • [EXTERNAL_DOWNLOADS]: The skill recommends the installation of the chrome-devtools-mcp package from the NPM registry using the npx utility to enable required MCP tools.
  • [COMMAND_EXECUTION]: Provides a command snippet for the user to include in their MCP configuration file, which involves the execution of the chrome-devtools-mcp tool through npx.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 08:10 PM
Security Audit — agent-trust-hub — web-perf