@brainervirus/workit-opencode@1.2.0
Workit OpenCode plugin — native tools, adaptive policy, and fourteen method skills
AI Security Review
scanned 21d ago · by lpm-firewall-aiDirect inspection supports ordinary workflow plugin behavior, with supplied service credentials and guarded setup operations. The scanner's gateway and command-output exfiltration labels were not substantiated by the inspected source flows.
Decision evidence
public snapshot- package.json has only build and typecheck scripts, no installation hooks or runtime self-dependency.
- Plugin configuration changes require a confirmed tool invocation.
- YouTrack setup asks users to supply a token for the configured service.
- GitLab verification sends the configured token to the configured GitLab user API.
- Command execution uses explicit executable arguments and a repository working directory.
- The active V2 tool rejects external operations other than context reads.
- The plugin handles service credentials, executes development commands, and writes workflow configuration; these capabilities warrant scrutiny but inspected flows match its functionality.
Source & flagged code
5 flagged · loading sourceManifest-reachable source sends a prompted API credential to a fixed unofficial gateway and persists the redirection.
dist/plugin.jsView on unpkgFindings
Affected versions and remediation
This report applies to @brainervirus/workit-opencode@1.2.0.
See all versions of @brainervirus/workit-opencode for other recorded verdicts.
- Review the evidence and your use of @brainervirus/workit-opencode@1.2.0 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.