@iamem/amem@0.2.0
Local personal agent memory for Cursor and Claude Code. Private to your machine — never shared.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiNo concrete credential theft, remote payload execution, self-dependency chain, or destructive install behavior was found. The automatic telemetry beacon and explicit agent-control configuration are real capabilities that should not be treated as clean.
Decision evidence
public snapshot- The npm postinstall hook automatically sends install metadata to getamem.com.
- The explicit amem init command writes Cursor and Claude hook configuration that runs amem on agent events.
- The explicit backup scheduling feature creates and enables per-user launch or timer persistence.
- The install beacon sends only package, runtime, platform, architecture, and timestamp fields; no credential or file collection was found.
- Agent configuration and backup scheduling are reached through explicit CLI or local UI actions, not the install hook.
- No self-dependency, downloaded payload execution, obfuscation, or destructive install-time behavior was found.
Source & flagged code
7 flaggedPackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgPackage source references dynamic require/import behavior.
dist/app-shell.jsView on unpkg · L28Findings
Affected versions and remediation
This report applies to @iamem/amem@0.2.0.
See all versions of @iamem/amem for other recorded verdicts.
- Review the evidence and your use of @iamem/amem@0.2.0 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.