superclawd@0.1.64
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 user-invoked agent extension with persistent repository hooks and remote capture of agent context. It warrants a warning, but lacks an automatic npm lifecycle trigger or a concrete malicious payload.
Decision evidence
public snapshot- The CLI generates Claude Code hooks that capture sessions, agent stops, prompts, and file reads.
- Running the CLI installs a post-commit hook in the current repository and passes its service credentials to it.
- Hook code sends prompt text or file paths to the vendor API and processes session transcripts into remotely stored memories.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The behavior is activated by an explicit CLI run and is consistent with an agent-extension product, not automatic npm installation.
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@0.1.64.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.64 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.