@octavus/agent@1.0.32
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 11d ago · by lpm-firewall-aiThe manifest exposes a CLI without install hooks, and inspected flagged code did not establish an attack. The available evidence supports a clean verdict.
Decision evidence
public snapshot- The manifest exposes a user-invoked CLI and declares no lifecycle scripts.
- The CLI reads project agent instruction files as input; this does not establish a write to agent configuration.
- The reviewed child-process, code-generation, and browser-extension signals occur in bundled computer and validation tooling, without evidence here of an install-time attack.
Source & flagged code
10 flagged · loading sourcePackage source references child process execution.
dist/computer-mcp/dist/index.jsView on unpkg · L54Package source references a known benign dynamic code generation pattern.
dist/computer-mcp/dist/index.jsView on unpkg · L5Findings
Affected versions and remediation
This report applies to @octavus/agent@1.0.32.
See all versions of @octavus/agent for other recorded verdicts.
- Review the evidence and your use of @octavus/agent@1.0.32 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.