superclawd@0.1.81
Claude Code, supercharged — your team's standards, every session. The superclawd CLI loads your workspace's skills, agents, commands, workflows, and live directives into Claude Code as a plugin.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThis is not an install-time malware chain, but its explicit CLI workflow creates an AI-agent control surface and uploads session-derived content to remote services. The bundled AI-operating instructions increase the risk of unreviewed remote control, so a warning is warranted.
Decision evidence
public snapshot- The user-invoked CLI creates a Claude Code plugin and broad session hooks.
- The helper processes finished session transcripts and sends derived memories to the package backend.
- Bundled instructions tell the AI to fetch remote directives before acting and to persist durable instructions.
- The CLI can add a project post-commit hook that runs the helper in the background.
- The manifest has no preinstall, install, or postinstall lifecycle hook.
- The risky behavior requires the user to run the CLI, authenticate, and launch a session.
- The network hosts are package-aligned SuperClawd services.
- No self-dependency, hidden payload download, or arbitrary credential-file harvesting was found.
Source & flagged code
7 flaggedPackage source references a known benign dynamic code generation pattern.
dist/mcp-server.mjsView on unpkg · L5Findings
Affected versions and remediation
This report applies to superclawd@0.1.81.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.81 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.