Browswer Automation

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its browser automation capabilities.
  • Ingestion points: External web content is ingested into the agent's context when performing agent-browser snapshot -i as described in SKILL.md.
  • Boundary markers: The instructions do not define delimiters or specific system prompts to isolate retrieved web content from the agent's core instructions.
  • Capability inventory: The skill utilizes the agent-browser CLI tool (SKILL.md) to interact with web pages and execute automation commands.
  • Sanitization: There is no mention of content filtering or sanitization for the data retrieved from external URLs.
  • [COMMAND_EXECUTION]: The skill relies on the execution of the agent-browser CLI tool to perform its primary functions. While this is the intended purpose of the skill, it involves subprocess execution based on user-provided URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 09:06 PM