core-agent-browser

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documents the usage of a browser automation CLI tool. The commands described, such as navigation, snapshotting, and element interaction, are standard for web automation workflows and do not exhibit malicious patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest data from external websites via a browser, which introduces a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent context through agent-browser snapshot, agent-browser get text, agent-browser get value, and agent-browser get title commands documented in SKILL.md.
  • Boundary markers: The skill instructions do not specify explicit delimiters or "ignore embedded instructions" warnings for the content retrieved from the browser.
  • Capability inventory: The skill utilizes the agent-browser CLI to perform navigation, interactive element manipulation (click, fill, type), and information retrieval from remote URLs.
  • Sanitization: No specific sanitization, filtering, or validation logic is defined within the instructions for handling the untrusted external content returned by the browser commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:57 AM
Security Audit — agent-trust-hub — core-agent-browser