superlocalmemory@4.2.8
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-aiThe flagged lifecycle and hook behavior is consistent with setting up and operating the package’s local memory runtime. The inspected source shows no concrete malicious behavior or unresolved attack surface.
Decision evidence
public snapshot- The postinstall hook creates an environment inside the package and installs its matching Python runtime there.
- The flagged list, profile, recall, and remember hooks pass command-line arguments to corresponding memory commands.
- The reset hook warns about data deletion and asks for confirmation before a soft reset.
- The postinstall media step uses an explicit request or a default-no interactive prompt and skips interactive prompts in CI.
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@4.2.8.
See all versions of superlocalmemory for other recorded verdicts.
- Review the evidence and your use of superlocalmemory@4.2.8 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.