skills/browserbase/skills/functions/Gen Agent Trust Hub

functions

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for executing commands via the Browserbase CLI for local development and cloud deployment.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to download and initialize a project using the official Browserbase SDK package from the npm registry.
  • [DATA_EXFILTRATION]: The skill provides instructions for managing sensitive API keys and project identifiers using environment files for authorized communication with Browserbase APIs.
  • [PROMPT_INJECTION]: The skill's architecture for processing external URLs and selectors as input parameters for browser automation represents a surface for indirect prompt injection.
  • Ingestion points: Data enters the function through the params object in SKILL.md and REFERENCE.md.
  • Boundary markers: No boundary markers or instructions to ignore embedded commands are present in the provided code snippets.
  • Capability inventory: The skill enables browser automation via Playwright (playwright-core) and allows publishing functions to the cloud.
  • Sanitization: The provided examples do not demonstrate sanitization or validation of input parameters before use.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 02:11 PM
Security Audit — agent-trust-hub — functions