web-perf
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends a configuration using 'npx -y chrome-devtools-mcp@latest' to download and run the required MCP server from the NPM registry.
- [COMMAND_EXECUTION]: The workflow involves executing browser-related tools like 'navigate_page', 'performance_start_trace', and 'take_snapshot' via the MCP server. It also performs filesystem operations to detect and analyze build configurations such as 'webpack.config.js', 'vite.config.js', and 'package.json' within the local codebase.
- [PROMPT_INJECTION]: The skill exposes the agent to indirect prompt injection risks by processing content from untrusted external URLs. Ingestion points: Data is ingested through 'navigate_page' and 'take_snapshot' during performance and accessibility audits. Boundary markers: The instructions lack specific markers or instructions to treat external web content as untrusted data or to ignore embedded commands. Capability inventory: The skill possesses capabilities to list network requests, view detailed request headers, take accessibility snapshots, and read local configuration files. Sanitization: No mechanisms for sanitizing or validating external content are described in the workflow.
Audit Metadata