osborn@0.9.164
Voice AI coding assistant - local agent that connects to Osborn frontend
AI Security Review
scanned 2mo ago · by lpm-firewall-aiSource inspection does not establish malicious intent or automatic installation-time compromise. The remote download-and-execute path and broad Claude configuration mutation are still material runtime risks that warrant a warning.
Decision evidence
public snapshot- A frontend data-channel command can trigger a shell pipeline that downloads and executes the code-server installer.
- Importing the Claude integration changes the user's global Claude settings file without a separate setup command.
- The runtime starts only through the user-invoked CLI, but it exposes high-impact local-agent capabilities.
- The manifest has no install, postinstall, or preinstall hook; prepublishOnly runs only when publishing.
- The reviewed network calls are feature-aligned service calls; no source evidence sends harvested environment values or command output to an unrelated endpoint.
Source & flagged code
9 flagged · loading sourceThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
bin/cli.jsView on unpkgPackage source references dynamic require/import behavior.
dist/jsonl-search.jsFindings
Affected versions and remediation
This report applies to osborn@0.9.164.
See all versions of osborn for other recorded verdicts.
- Review the evidence and your use of osborn@0.9.164 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.