Skills
skills/quuu/skills/functions/Gen Agent Trust Hub

functions

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data which creates a surface for indirect prompt injection.\n
  • Ingestion points: User-provided inputs are accessed via the context.params object in the function code within index.ts.\n
  • Boundary markers: There are no explicit boundary markers or instructions to treat the parameters as untrusted data.\n
  • Capability inventory: The skill utilizes the Browserbase CLI (bb) and Playwright for browser automation, which involve network operations and potentially sensitive site interactions across all scripts.\n
  • Sanitization: The provided code snippets do not demonstrate sanitization or validation of the input parameters before they are used in browser actions.\n- [EXTERNAL_DOWNLOADS]: Fetches and executes the official @browserbasehq/sdk-functions package from the npm registry using pnpm dlx for project initialization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 05:11 PM