openchamber-sogawugu@1.21.1
[![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-aiThis is a suspicious, impersonation-like package with high-impact runtime agent-control features, but the observed writes require explicit runtime actions and there is no install hook. The evidence supports a warning rather than a publication block.
Decision evidence
public snapshot- The package uses an unrelated suffixed name while exposing the `openchamber` command.
- Its running HTTP service accepts skill content and creates agent skills in user or project agent directories.
- The optional startup command snapshots most environment variables and writes a login service, preserving credentials for later execution.
- The manifest has no preinstall, install, or postinstall hook.
- The persistence path requires the explicit `openchamber startup enable` command.
- No source inspected showed automatic secret exfiltration or a remote payload executed during installation.
Source & flagged code
11 flaggedFindings
Affected versions and remediation
This report applies to openchamber-sogawugu@1.21.1.
See all versions of openchamber-sogawugu for other recorded verdicts.
- Review the evidence and your use of openchamber-sogawugu@1.21.1 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.