@xfive/chisel-ai-toolkit@1.3.0
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-aiThe automatic postinstall setup writes first-party agent instructions and a project-scoped Claude hook without an installation-time consent check. The inspected behavior supports a warning for agent extension lifecycle risk, but does not establish a concrete attack or malicious intent.
Decision evidence
public snapshot- The postinstall hook runs install.js automatically during package installation.
- The installer selects Claude and Agents by default and invokes their emitters for the detected theme root.
- The Claude emitter adds package skills to the theme’s .claude directory and installs a guard hook in Claude settings.
- The hook is project-scoped at .claude/settings.json and runs on editing tools.
- Uninstall removes the package’s managed instructions and its hook while retaining other settings.
- The inspected source establishes automatic first-party agent setup, but no credential transfer, remote endpoint, or separate concrete attack.
- The installer supports a dry-run option, but that option is not enabled by the postinstall script.
- The guard hook is installed in project settings and has a defined removal path.
Source & flagged code
6 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgA bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to @xfive/chisel-ai-toolkit@1.3.0.
See all versions of @xfive/chisel-ai-toolkit for other recorded verdicts.
- Review the evidence and your use of @xfive/chisel-ai-toolkit@1.3.0 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.