@netnodeag/kraftwerk@0.55.0
Open-source agentic workspace for teams — where people and AI agents get work done together: agents (Claude Code, Codex, Pi), skills, shared knowledge, repeatable workflows, and deterministic verification
AI Security Review
scanned 17d ago · by lpm-firewall-aiSource inspection found no consumer install lifecycle hook or concrete malicious behavior. The scanner's execution, shell, and Unicode hints map to user-invoked product features and editor code.
Decision evidence
public snapshot- package.json has a publish-time build hook but no consumer install hook.
- The flagged skills location discovers project and user skills; skill changes go through an agent-specific API and write path.
- The flagged run operation lists run directories and reads their records.
- The inspector bundles contain editor and parser code; the invisible spacing character in the editor bundle is used as a spacing fallback.
- The runner starts a requested workflow, and the remote helper clones a specified repository into a cache.
- Vibeable development commands run through an explicit start endpoint; tunnel startup requires project tunnel configuration.
Source & flagged code
8 flaggedThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/inspector/vibeables.jsView on unpkgFindings
Affected versions and remediation
This report applies to @netnodeag/kraftwerk@0.55.0.
See all versions of @netnodeag/kraftwerk for other recorded verdicts.
- Review the evidence and your use of @netnodeag/kraftwerk@0.55.0 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.