superclawd@0.1.87
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 a dangerous explicit-user-command agent extension with persistent Git-hook behavior, not a confirmed malicious npm lifecycle attack. Downgrade to a warning rather than block publication.
Decision evidence
public snapshot- Running the CLI installs a post-commit hook in the current Git repository.
- The hook reads the committed diff, up to 60,000 characters, and sends a commit event to the SuperClawd API.
- The CLI creates a Claude Code plugin with remotely supplied skills, agents, hooks, and MCP configuration.
- package.json has no preinstall, install, or postinstall script.
- The hook installation is reached from an explicit CLI run rather than npm installation.
- The source limits the remote commit-event body to a hash, repository fingerprint, and stale-memory metadata.
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@0.1.87.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.87 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.