skills/tul-sh/skills/agent-browser/Gen Agent Trust Hub

agent-browser

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is configured to allow the agent to execute any sub-command of the inference.sh CLI using the Bash(infsh *) permission string defined in the allowed-tools metadata.\n- [REMOTE_CODE_EXECUTION]: Through the execute function, the skill allows for the execution of arbitrary JavaScript code within the context of the remote browser session. This is a powerful feature intended for scraping and automation but represents a dynamic code execution vector.\n- [DATA_EXFILTRATION]: Documentation in references/authentication.md and templates/capture-workflow.sh provides examples of using JavaScript to extract sensitive information, including browser cookies and full-page text content, which could be exfiltrated if the agent is compromised.\n- [PROMPT_INJECTION]: The skill possesses a significant surface for indirect prompt injection because it is designed to ingest and process data from arbitrary, untrusted web sources.\n
  • Ingestion points: Untrusted data enters the agent context through the open, snapshot, and execute functions, as seen in SKILL.md and templates/capture-workflow.sh.\n
  • Boundary markers: The skill does not implement boundary markers or instructions to the agent to ignore embedded commands within the extracted web content.\n
  • Capability inventory: The agent has extensive capabilities to interact with the environment, including click, fill, upload, and execute (JavaScript), which could be triggered by instructions found on a malicious webpage.\n
  • Sanitization: No sanitization or filtering of external web content is performed before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 08:26 AM