@xfive/chisel-ai-toolkit@1.5.0
Chisel AI toolkit — skills, rules and reference docs for AI coding agents working on Chisel WordPress themes
AI Security Review
scanned 6d ago · by lpm-firewall-aiInstallation automatically registers a first-party Claude hook that changes agent behavior by blocking edits in the theme’s core directory. The behavior is narrow and package-aligned, but its automatic activation warrants a warning for agent extension lifecycle risk.
Decision evidence
public snapshot- The package runs its installer automatically after installation.
- The installer defaults to Claude and AGENTS, then runs each selected emitter.
- The Claude emitter installs a local hook and registers it in the project’s Claude settings.
- The registered hook blocks edits under the project’s core directory; it does not contact a network endpoint.
- Uninstall removes the toolkit’s hook while preserving other settings.
- The hook is narrowly scoped to the project’s core directory and serves the toolkit’s stated theme-protection function.
Source & flagged code
6 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgThe package runs its installer automatically after installation.
package.jsonView on unpkg · L23Findings
Affected versions and remediation
This report applies to @xfive/chisel-ai-toolkit@1.5.0.
See all versions of @xfive/chisel-ai-toolkit for other recorded verdicts.
- Review the evidence and your use of @xfive/chisel-ai-toolkit@1.5.0 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.