open-walnut@0.6.9
Personal AI powered by Claude — task management, Claude Code sessions, memory system, and web UI
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe automatic hook’s attempted removal of an SDK safety reminder is a concrete agent-control risk. The source does not confirm that the patch is successfully applied, so this is suspicious rather than a verified control hijack.
Decision evidence
public snapshot- The manifest runs scripts/postinstall.mjs automatically after installation.
- The postinstall script locates the installed Claude Agent SDK and attempts to replace text in its CLI file.
- The shipped patch removes a Claude SDK system reminder about safe malware analysis; whether the install-time patch applies as intended remains unclear.
- The patch is narrowly tied to a specific SDK patch file and checks that the installed SDK version matches its target.
- The inspected source does not establish that the attempted reminder change succeeds.
Source & flagged code
18 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@0.6.9.
See all versions of open-walnut for other recorded verdicts.
- Review the evidence and your use of open-walnut@0.6.9 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.