superlocalmemory@4.2.0
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 10d ago · by lpm-firewall-aiInspected source shows bounded runtime setup and user-invoked CLI wrappers, with confirmation before destructive reset actions. The scanner similarity and lifecycle hints do not establish malicious behavior.
Decision evidence
public snapshot- package.json declares a postinstall hook and lists docx as its runtime dependency.
- The postinstall script creates a package-local virtual environment and installs the Python distribution at the exact package version.
- Media setup records a request only after an explicit flag or an affirmative response to a default-No prompt.
- The list, recall, and remember hooks pass their supplied arguments to corresponding Python CLI commands.
- The profile hook prompts before deleting a profile; the reset hook requires typing a confirmation phrase before a hard reset.
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@4.2.0.
See all versions of superlocalmemory for other recorded verdicts.
- Review the evidence and your use of superlocalmemory@4.2.0 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.