gologin-local-agent-browser-skill
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill's primary function is to execute the
gologin-local-agent-browserCLI to interact with local browser profiles, perform web navigation, and manage automation jobs. - [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
gologin-local-agent-browser-clipackage via npm and provides links to the official GologinLabs GitHub repositories for source-based installation. - [DYNAMIC_EXECUTION]: The skill supports dynamic interaction with web pages through an
evaltool that executes JavaScript in the browser and aruncommand that processes automation steps defined in JSON runbooks. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill includes tools to export browser state, such as
cookiesandstorage-export, to support session persistence between runs. These tools are governed by instructions requiring an active GoLogin token. - [INDIRECT_PROMPT_INJECTION]: As a tool that reads and interacts with external web content via the
snapshotandopentools, it has a natural exposure to indirect prompt injection. The skill mitigates this by instructing the agent to maintain strict control over session state and to verify user intent for sensitive actions.
Audit Metadata