@netnodeag/kraftwerk@0.21.1
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 2mo ago · by lpm-firewall-aiStatic inspection found no registry-install lifecycle hook, self-dependency, hidden payload execution, or unconsented agent-control-surface mutation. The flagged primitives are consistent with an explicitly invoked agent workflow CLI.
Decision evidence
public snapshot- The manifest has only a prepublish hook; installation has no preinstall, install, or postinstall script.
- The flagged npm install is limited to building missing inspector assets in a development checkout, while published packages require shipped assets.
- Remote cloning, Docker execution, and agent workflows are activated by explicit CLI or UI actions.
- The inspector filters discovered skills through a team-member allowlist and does not automatically alter agent configuration.
- The package can clone user-supplied Git repositories and run Git commands.
- Explicit sandbox runs can pass named API-key variables and optionally an SSH agent into Docker.
- The inspector can launch user-requested workflows through npx.
Source & flagged code
5 flaggedPackage source references dynamic require/import behavior.
bin/kraftwerk.jsView on unpkg · L15Findings
Affected versions and remediation
This report applies to @netnodeag/kraftwerk@0.21.1.
See all versions of @netnodeag/kraftwerk for other recorded verdicts.
- Review the evidence and your use of @netnodeag/kraftwerk@0.21.1 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.