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

web-perf

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to configure their environment by running npx -y chrome-devtools-mcp@latest. This command downloads and executes a package from the NPM registry at runtime.\n- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to audit external web pages, creating a vulnerability surface where malicious content could attempt to influence the agent.\n
  • Ingestion points: Untrusted data from external URLs is ingested through navigate_page and take_snapshot (SKILL.md).\n
  • Boundary markers: The instructions do not define delimiters or provide warnings to the agent to ignore instructions that might be embedded in the audited web content.\n
  • Capability inventory: The skill utilizes a suite of browser automation, network auditing, and performance profiling tools.\n
  • Sanitization: The skill does not implement sanitization or validation for the DOM tree or network request data before the agent processes it.\n- [COMMAND_EXECUTION]: The skill recommends that the user execute a shell command (npx) to initialize the required local tooling.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 05:22 PM