superclawd@0.1.65
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 not a malicious install hook because package installation does not execute it, but the runtime agent integration creates hooks and uploads transcript-derived data. The package warrants a warning for its persistent AI-agent extension behavior.
Decision evidence
public snapshot- The user-run CLI creates Claude hooks for prompt retrieval and session capture.
- The CLI writes an executable post-commit hook into the current repository.
- The hook helper reads a session transcript and posts generated memory records to the SuperClawd API.
- package.json has no npm preinstall, install, or postinstall hook.
- The control-surface changes occur only after the user invokes the CLI; no self-dependency is present.
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@0.1.65.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.65 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.