skills/mksglu/skills/web-perf/Gen Agent Trust Hub

web-perf

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes content from external websites.
  • Ingestion points: Data enters the system via the navigate_page tool when auditing external URLs.
  • Boundary markers: Absent; the instructions do not include delimiters or warnings to ignore commands embedded in the audited pages.
  • Capability inventory: The skill can navigate to pages and perform performance traces.
  • Sanitization: None; external data is processed as-is.
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the chrome-devtools-mcp package using npx to enable the required MCP functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 04:33 AM