osborn@0.9.263
⚠ Under reviewVoice AI coding assistant - local agent that connects to Osborn frontend
AI Security Review
scanned 1d ago · by lpm-firewall-aiThe inspected source shows ordinary remote tool proxying and no confirmed attack. Selected dependency behavior remains unresolved, so the package cannot be cleared as clean from this review.
Decision evidence
public snapshot- package.json declares ranged runtime dependencies on Claude Agent SDK and Anthropic SDK, so their behavior can affect package runtime.
- The Smithery proxy connects to a configured remote MCP server and registers its tools locally; the inspected code does not establish harmful behavior, but the dependency-backed behavior remains incompletely resolved.
- The manifest has no install lifecycle hook; its prepublishOnly script runs the build.
- The inspected Smithery proxy forwards remote tools, and no concrete credential theft or other attack was established.
Source & flagged code
9 flagged · loading sourcePackage source references dynamic require/import behavior.
dist/jsonl-search.jsView on unpkg · L34Findings
Affected versions and remediation
This report applies to osborn@0.9.263.
See all versions of osborn for other recorded verdicts.
- Review the evidence and your use of osborn@0.9.263 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.