openchamber-sogawugu@1.21.6
[![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-aiNo evidence supports a malicious npm install chain or data theft. The package nevertheless provides explicit-user-command mutation of external AI-agent skill surfaces and persistence, so it should be warned rather than marked clean.
Decision evidence
public snapshot- The running application can create and modify skill files for OpenCode, Claude, and Agents locations.
- An explicit startup enable command installs a persistent user service.
- The package launches and manages an OpenCode coding-agent service.
- package.json has no preinstall, install, or postinstall hook.
- The startup service is reached only through the explicit startup enable subcommand.
- The managed agent plugin is written to the package data directory and points to a loopback endpoint.
- No source evidence shows secret exfiltration, remote payload execution, or automatic install-time mutation.
Source & flagged code
12 flaggedFindings
Affected versions and remediation
This report applies to openchamber-sogawugu@1.21.6.
See all versions of openchamber-sogawugu for other recorded verdicts.
- Review the evidence and your use of openchamber-sogawugu@1.21.6 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.