osborn@0.9.242
Voice AI coding assistant - local agent that connects to Osborn frontend
AI Security Review
scanned 25d ago · by lpm-firewall-aiThe source establishes runtime and command-triggered mutation of Claude's shared configuration surface. It does not establish malicious installation behavior, secret theft, or a remote payload.
Decision evidence
public snapshot- The package exposes command-line entrypoints rather than an install lifecycle hook.
- Running the LLM module changes shared Claude settings at module load.
- A frontend skill-add message writes caller-provided content into the user's Claude skills directory.
- The recall command can replace the user's Claude directory path with a workspace symlink.
- No package-install trigger, credential export sink, or unrelated network recipient was established in the inspected paths.
Source & flagged code
8 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@0.9.242.
See all versions of osborn for other recorded verdicts.
- Review the evidence and your use of osborn@0.9.242 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.