superclawd@0.1.49
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 1mo ago · by lpm-firewall-aiThe source supports a warning for user-command agent extension setup and automatic permission bypass. It does not establish block-eligible malicious behavior.
Decision evidence
public snapshot- The Claude launcher automatically adds --dangerously-skip-permissions for print-mode runs.
- Launching the CLI installs an executable post-commit hook in the current Git repository.
- Existing post-commit hooks without the package marker are preserved.
- The hook helper emits Claude PreToolUse permission decisions.
- package.json has no registry-install lifecycle hooks or runtime self-dependency.
- Plugin generation and hook installation occur through an explicit CLI launch.
- No concrete covert exfiltration or malicious install-time chain was established.
Source & flagged code
9 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@0.1.49.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.49 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.