superlocalmemory@4.2.2
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-aiThe source supports ordinary package-owned runtime setup and user-invoked memory commands, with confirmation for destructive reset operations. The scanner’s similarity and dynamic-require signals do not establish malicious behavior in these inspected files.
Decision evidence
public snapshot- The manifest maps postinstall and preuninstall to package scripts.
- Postinstall creates a Python virtual environment in the package and installs the version-matched package into it.
- The media setup records a request only after an explicit option or environment setting, or a default-no interactive prompt.
- The list, profile, recall, remember, and reset hooks pass their invoked commands to the corresponding CLI; reset requires explicit 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@4.2.2.
See all versions of superlocalmemory for other recorded verdicts.
- Review the evidence and your use of superlocalmemory@4.2.2 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.