superlocalmemory@4.2.4
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 lifecycle installer sets up the package's private Python runtime, and the flagged hooks dispatch user-supplied commands with confirmations for destructive actions. Source inspection found no concrete attack behavior.
Decision evidence
public snapshot- package.json runs a postinstall script; that script installs the matching Python package into its package-local runtime.
- The CLI launcher passes user arguments to the package-local Python runtime.
- The list, recall, and remember hooks dispatch to their matching memory commands and forward supplied arguments.
- Profile deletion requires typing the profile name, and switching requires an affirmative response.
- Soft reset requires an affirmative response; hard reset requires typing the exact confirmation phrase.
- Media setup is prompted with a default-no choice and only records a request after an affirmative choice.
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@4.2.4.
See all versions of superlocalmemory for other recorded verdicts.
- Review the evidence and your use of superlocalmemory@4.2.4 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.