superclawd@0.1.16
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 3mo ago · by lpm-firewall-aiNo install-time behavior or concrete malicious chain was found, so blocking is not supported. Automatic repository-hook persistence and remote agent-extension control are meaningful user-runtime risks.
Decision evidence
public snapshot- dist/index.js installs a post-commit hook on normal CLI launch.
- dist/hook-helper.mjs reads committed diffs and reports memory staleness to the service.
- Runtime plugin hooks send prompt/file-derived memory-search queries to the configured API.
- CLI creates a Claude plugin with remotely supplied skills, directives, and MCP servers.
- package.json has only prepublishOnly; no install-time hook.
- All observed network hosts are SuperClawd service endpoints.
- README describes workspace directives, MCP integration, and memory features.
- No hidden credential harvesting, unrelated receiver, or foreign agent-control mutation found.
Source & flagged code
7 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@0.1.16.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.16 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.