superclawd@0.1.76
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-aiThe behavior is user-invoked rather than an install-time attack, but it creates persistent repository hooks and captures AI-session and commit-related data for remote processing. That is a concrete agent-extension lifecycle and data-handling risk requiring a warning.
Decision evidence
public snapshot- Running the CLI in a Git repository writes a post-commit hook that launches this package in the background after every commit.
- The CLI installs Claude Code hooks for session, tool, and subagent events, including automatic capture paths.
- Captured session and commit-derived data is sent to the package service when configured credentials are present.
- The manifest has no preinstall, install, or postinstall hook.
- The package is a CLI entrypoint, so the behavior requires a user to invoke it.
Source & flagged code
8 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@0.1.76.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.76 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.