openchamber-sogawugu@1.21.5
[![GitHub stars](https://img.shields.io/github/stars/openchamber/openchamber?style=flat&logo=data%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIzMiIgaGVpZ2h0PSIzMiIgZmlsbD0iI2YxZWNlYyIgdmlld0JveD0iMCAwIDI1Ni
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe package has meaningful runtime control-surface and persistence capabilities, so it warrants a warning. It lacks npm install hooks and the inspected risky actions are not automatically triggered by installation.
Decision evidence
public snapshot- The runtime API creates user- or project-scoped AI-agent skill files.
- The CLI can install a per-user startup service on macOS and Linux.
- The server can probe the Cloudflare tunnel API at runtime.
- package.json has no preinstall, install, postinstall, or prepare lifecycle hook.
- The persistence and skill writes require running the application or using its API; they are not install-time actions.
- The child-process use in bin/cli.test.js is test code.
Source & flagged code
13 flaggedFindings
Affected versions and remediation
This report applies to openchamber-sogawugu@1.21.5.
See all versions of openchamber-sogawugu for other recorded verdicts.
- Review the evidence and your use of openchamber-sogawugu@1.21.5 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.