negotium@0.7.1
Install the Negotium multi-agent runtime and CLI with one package
AI Security Review
scanned 14d ago · by lpm-firewall-aiSource inspection found a postinstall binary setup with digest checks and runtime agent integrations using local credential checks and expected agent data paths. No concrete malicious behavior was established, so the package is clean.
Decision evidence
public snapshot- The postinstall invokes two package-owned installers that fetch versioned binaries from GitHub and verify SHA-256 digests before installation.
- The inspected credential helper checks whether Codex or Claude credentials exist; it does not send them. The peer bridge accepts only loopback HTTP destinations and requires a configured token.
- The inspected Claude integration writes rollout data into Claude’s project directory, consistent with the package’s agent runtime features.
- The package has a postinstall hook that downloads and installs executable binaries into its state directory.
- The package accesses local agent credential paths and Claude project files for runtime integration.
Source & flagged code
10 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgPackage source references child process execution.
dist/hosted-agent.jsView on unpkg · L9Findings
Affected versions and remediation
This report applies to negotium@0.7.1.
See all versions of negotium for other recorded verdicts.
- Review the evidence and your use of negotium@0.7.1 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.