gologin-agent-browser-skill

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs browser operations by invoking the gologin-agent-browser CLI, as specified in the manifest.json and tools.md files.
  • [EXTERNAL_DOWNLOADS]: Installation instructions in README.md direct users to download the gologin-agent-browser-cli from the NPM registry. This package is owned by the vendor GologinLabs.
  • [DATA_EXFILTRATION]: The agent_browser_upload tool enables the transfer of local files to a browser session. This intended functionality could be misused to exfiltrate sensitive files if the agent is directed to malicious sites. * Ingestion points: Content is ingested from external websites via agent_browser_snapshot, agent_browser_get, and agent_browser_find. * Boundary markers: No delimiters or instructions to ignore embedded content were found. * Capability inventory: The skill can execute CLI commands and interact with the file system for uploads and downloads. * Sanitization: No explicit sanitization of untrusted web content is described in the skill metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 06:37 PM