web-perf

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to configure the chrome-devtools-mcp package from the NPM registry to provide the necessary analysis tools.
  • [COMMAND_EXECUTION]: The agent is directed to analyze local codebase configuration files (e.g., package.json, webpack.config.js) to identify optimization opportunities for the developer.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes data from untrusted external URLs and local project files.
  • Ingestion points: Web page content and accessibility trees retrieved through tool calls specified in SKILL.md.
  • Boundary markers: No explicit delimiters are used to separate untrusted tool output from the agent's instructions.
  • Capability inventory: The skill utilizes network navigation and local filesystem read access via the associated MCP server.
  • Sanitization: No specific sanitization or filtering logic is defined for the content retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 12:53 PM
Security Audit — agent-trust-hub — web-perf