@brainervirus/workit-opencode@6.0.1
Workit OpenCode plugin — native tools, adaptive policy, and sixteen method skills
AI Security Review
scanned 17d ago · by lpm-firewall-aiThe flagged command, environment, and network primitives are consistent with the inspected workflow plugin implementation. Source inspection did not establish a malicious execution or exfiltration chain.
Decision evidence
public snapshot- package.json has only build and typecheck scripts, no install lifecycle hooks or runtime self-dependency.
- Plugin tool execution checks that the session belongs to the plugin workspace.
- Initialization changes require an explicit confirmed argument.
- The shell permission hook preserves existing denials and can add denials.
- Command execution uses argument arrays and a repository working directory; inspected network code uses explicitly configured YouTrack credentials.
Source & flagged code
5 flagged · loading sourceSource combines command execution, command-output handling, and outbound requests; review data flow before blocking.
dist/plugin.jsView on unpkg · L6Findings
Affected versions and remediation
This report applies to @brainervirus/workit-opencode@6.0.1.
See all versions of @brainervirus/workit-opencode for other recorded verdicts.
- Review the evidence and your use of @brainervirus/workit-opencode@6.0.1 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.