superlocalmemory@4.2.5
The governed memory brain for AI agents: one local memory for Claude Code, Codex, Cursor, Copilot, ChatGPT and any MCP client. Honest recall, documents and pictures, roles, audit and GDPR erasure.
AI Security Review
scanned 9d ago · by lpm-firewall-aiSource inspection found a package-aligned runtime installation and locally invoked command handlers with confirmation for destructive operations. The scanner similarity hints do not establish malicious behavior in these files.
Decision evidence
public snapshot- The manifest runs scripts/postinstall.js during installation; the installer installs the versioned superlocalmemory package into its private runtime.
- Optional media setup is requested through an explicit setting or an interactive prompt that defaults to no.
- The list, recall, and remember handlers pass their corresponding command and supplied arguments to the local CLI.
- Profile and reset handlers require confirmation for destructive actions.
Source & flagged code
11 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 unpkgSource file is highly similar to a previously finalized malicious package; route for source-aware review.
Findings
Affected versions and remediation
This report applies to superlocalmemory@4.2.5.
See all versions of superlocalmemory for other recorded verdicts.
- Review the evidence and your use of superlocalmemory@4.2.5 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.