@octavus/agent@1.0.9
Octavus Agent CLI - run one of your cloud Octavus Agents on a machine you control, using that machine as the agent's computer. The agent lives in the cloud (fully configured and observable); the local machine only supplies the computer and the trigger.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe static signals arise from bundled automation components, including standard schema code and explicit local MCP services. There are no lifecycle hooks or confirmed stealthy payload, harvesting, or exfiltration behavior.
Decision evidence
public snapshot- The user-invoked CLI connects to an operator relay with a computer token.
- The bundled filesystem MCP server can modify files within client-provided allowed roots.
- The browser extension accepts commands only over a localhost WebSocket.
- The computer component imports child-process execution APIs for its automation runtime.
- The browser MCP launcher binds its local server to localhost.
- package.json has no preinstall, install, postinstall, or other lifecycle script.
- The only package entry point is the octoagent CLI.
- No hidden payload reconstruction or unconsented credential exfiltration was confirmed.
- Network control is initiated by an explicit CLI run using configured credentials.
Source & flagged code
10 flagged · loading sourcePackage source references child process execution.
dist/computer-mcp/dist/index.jsView on unpkg · L53Source file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/computer-mcp/dist/index.jsView on unpkgFindings
Affected versions and remediation
This report applies to @octavus/agent@1.0.9.
See all versions of @octavus/agent for other recorded verdicts.
- Review the evidence and your use of @octavus/agent@1.0.9 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.