@netnodeag/kraftwerk@0.23.0
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 2mo ago · by lpm-firewall-aiThis is an agentic workflow CLI with powerful but user-invoked command execution and sandbox features. It has no registry install hook, self-dependency chain, stealth persistence, or confirmed exfiltration behavior.
Decision evidence
public snapshot- User-selected workflows can execute Bash scripts.
- The optional Docker runner forwards selected API keys and SSH access only when requested.
- Remote workflow sources are cloned into a local cache.
- The inspector can launch a user-requested workflow through npx.
- The chat module describes workflow execution as a user-directed action.
- The manifest has only a publish-time build hook, not an install lifecycle hook.
- No preinstall, install, or postinstall script is present.
- No secret collection or outbound exfiltration code was found.
- No runtime dependency on this package itself is declared.
- Risky execution features are explicit CLI, workflow, UI, or sandbox functions.
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@0.23.0.
See all versions of @netnodeag/kraftwerk for other recorded verdicts.
- Review the evidence and your use of @netnodeag/kraftwerk@0.23.0 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.