skills/involvex/aetheris/web-perf/Gen Agent Trust Hub

web-perf

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows best practices for web performance auditing and uses standard, well-documented MCP tools for browser interaction.- [EXTERNAL_DOWNLOADS]: The skill provides instructions for the user to install the 'chrome-devtools-mcp' package from the NPM registry, which is a well-known and standard service for this ecosystem.- [PROMPT_INJECTION]: There is a surface for indirect prompt injection because the skill navigates to external target URLs and processes their content. 1. Ingestion points: navigate_page (SKILL.md) 2. Boundary markers: Absent 3. Capability inventory: navigate_page, list_network_requests, get_network_request, performance_start_trace, take_snapshot (SKILL.md) 4. Sanitization: Absent. This risk is inherent to any tool designed to browse and audit the live web.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 04:43 PM