superlocalmemory@4.2.9
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 6d ago · by lpm-firewall-aiSource inspection found a package-local runtime installer and user-invoked product commands, with opt-in or confirmation for the inspected settings and destructive actions. The static similarity and lifecycle signals did not establish malicious behavior.
Decision evidence
public snapshot- The manifest runs scripts/postinstall.js after installation.
- The installer creates a package-local Python environment and runs pip through that environment.
- The media setup step records a request only after an explicit setting or a default-No terminal prompt.
- The flagged list, profile, recall, and remember scripts dispatch their named product commands with supplied arguments.
- The reset script requires confirmation before performing a soft reset.
Source & flagged code
10 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@4.2.9.
See all versions of superlocalmemory for other recorded verdicts.
- Review the evidence and your use of superlocalmemory@4.2.9 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.