open-walnut@0.6.12
Personal AI powered by Claude — task management, Claude Code sessions, memory system, and web UI
AI Security Review
scanned 8d ago · by lpm-firewall-aiThe automatic install hook suppresses a safety reminder in the package's Claude Agent SDK dependency, and the package later uses that SDK for agent sessions. The source supports a warning for agent lifecycle risk, but does not establish a broader concrete attack.
Decision evidence
public snapshot- The npm postinstall hook automatically runs the package installer.
- The installer patches the installed Claude Agent SDK CLI when its version matches the shipped patch.
- The patch removes the SDK reminder that tells the agent to consider malware when reading files and limits assistance that would improve malware.
- The CLI imports the patched SDK when starting agent sessions.
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@0.6.12.
See all versions of open-walnut for other recorded verdicts.
- Review the evidence and your use of open-walnut@0.6.12 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.