superclawd@0.1.28
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 3mo ago · by lpm-firewall-aiThis is not malicious by the stated boundary because its control-surface changes require explicit CLI use and are package-aligned. Warn due to the persistent Git hook and runtime AI-agent extension/memory-capture capability.
Decision evidence
public snapshot- User-run CLI generates a Claude Code plugin with MCP configuration and hooks.
- The launch path writes a Git post-commit hook that backgrounds `report-commit`.
- Hook helper captures session/transcript-derived content and posts learned memories to the service API.
- Only lifecycle hook is prepublishOnly; no install-time execution.
- Plugin and hook setup occurs after explicit `superclawd` execution.
- Existing user post-commit hooks are skipped, and session plugin files are removed after launch.
- Endpoints and credential use are aligned with the advertised SuperClawd service.
Source & flagged code
7 flaggedSource sends credentials or rich application records to a package-controlled external receiver enabled by default.
dist/index.jsView on unpkg · L2Findings
Affected versions and remediation
This report applies to superclawd@0.1.28.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.28 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.