@roll-agent/browser-use-agent@0.27.0
AI Security Review
scanned 27d ago · by lpm-firewall-aiThis is a concrete conditional forwarding capability with an unrestricted operator-configured destination, but it has no automatic install trigger and requires configuration. It warrants a warning rather than a publication block.
Decision evidence
public snapshot- The active entrypoint enables recruitment-event tracking unless disabled and permits an environment-selected API base URL.
- When configured, tracking sends an environment token and event body in an HTTP POST request.
- Browser message events include candidate names, message previews, and conversation identifiers.
- The manifest has no preinstall, install, or postinstall lifecycle hook.
- The remote request requires both a token and an agent identifier before it runs.
Source & flagged code
4 flagged · loading sourceSource sends credentials or rich application records to a package-controlled external receiver enabled by default.
dist/index.jsView on unpkg · L1A single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/index.jsFindings
Affected versions and remediation
This report applies to @roll-agent/browser-use-agent@0.27.0.
See all versions of @roll-agent/browser-use-agent for other recorded verdicts.
- Review the evidence and your use of @roll-agent/browser-use-agent@0.27.0 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.