open-walnut@0.6.13
Personal AI powered by Claude — task management, Claude Code sessions, memory system, and web UI
AI Security Review
scanned 7d ago · by lpm-firewall-aiThe install-time removal of an agent safety reminder presents a concrete but bounded agent lifecycle risk. The inspected source does not establish a publish-blocking attack.
Decision evidence
public snapshot- The package runs a postinstall script during installation.
- The install script writes a version-matched patch into the installed Claude Agent SDK CLI.
- The patch removes a reminder directing the assistant to refuse improving malware.
- The package pins the SDK version that the patch targets.
- The flagged configuration-path matches are ordinary path references; no attack was established from them.
- The patch targets a specific SDK version and changes that SDK’s CLI file; inspected source did not establish credential theft, persistence, or remote execution.
Source & flagged code
26 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 unpkgPackage source references child process execution.
dist/plugin-store/walnut-rhythm/dist/server.mjsView on unpkg · L8Findings
Affected versions and remediation
This report applies to open-walnut@0.6.13.
See all versions of open-walnut for other recorded verdicts.
- Review the evidence and your use of open-walnut@0.6.13 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.