@octavus/agent@1.0.18
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 27d ago · by lpm-firewall-aiStatic inspection found an explicit CLI/MCP tool package without lifecycle hooks or a concrete malicious behavior. The indicated agent-related path reads instruction files rather than modifying agent configuration.
Decision evidence
public snapshot- The manifest exposes a CLI entrypoint and contains no lifecycle scripts.
- The main program acts on an explicit `run` command and accepts caller-provided prompt, workspace, and connection options.
- The indicated agent-integration code reads project instruction files for collection; the inspected excerpt shows no configuration write.
- The computer and code MCP bundles use standard input to receive transport data.
- The browser MCP bundle starts from command-line arguments, and the browser asset connects only to a loopback WebSocket.
- The filesystem MCP requires directories supplied through command-line arguments.
Source & flagged code
12 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@1.0.18.
See all versions of @octavus/agent for other recorded verdicts.
- Review the evidence and your use of @octavus/agent@1.0.18 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.