Skills
skills/browserbase/agent-browse/browser/Gen Agent Trust Hub

browser

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: browse snapshot, browse get text, and browse screenshot (SKILL.md, REFERENCE.md). Boundary markers: Absent. Capability inventory: click, type, fill, press, and eval (REFERENCE.md). Sanitization: Absent.
  • [EXTERNAL_DOWNLOADS]: The skill requires installing the @browserbasehq/browse-cli package from the NPM registry, which is an official tool from the vendor Browserbase.
  • [COMMAND_EXECUTION]: The skill uses the browse command-line tool for browser navigation, tab management, and page interaction.
  • [REMOTE_CODE_EXECUTION]: The browse eval command allows the execution of arbitrary JavaScript within the browser context to facilitate complex automation tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 07:50 PM