skills/eddiebelaval/squire/Verify/Gen Agent Trust Hub

Verify

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes common local development scripts via npm and npx, including type checking (tsc), linting, unit tests, and production builds.
  • [EXTERNAL_DOWNLOADS]: Leverages npx to run testing utilities, which may download packages from the public npm registry.
  • [PROMPT_INJECTION]: Contains a vulnerability surface for indirect prompt injection by processing external data from a web browser during automated testing.
  • Ingestion points: Processes data from browser_snapshot, browser_console_messages, and browser_network_requests.
  • Boundary markers: No explicit delimiters or warnings are present to instruct the agent to ignore instructions embedded in the browser output.
  • Capability inventory: The skill has the ability to execute shell commands (npm, npx) and interact with the local file system.
  • Sanitization: No specific validation or escaping is applied to the data retrieved from the Playwright MCP tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 02:42 AM
Security Audit — agent-trust-hub — Verify