@echomem/mcp@1.4.52
EchoMem MCP bridge for cross-agent memory, local history import, and recall
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe package has no install lifecycle hook, but its explicit setup path broadly changes AI-agent configuration and installs commands that persist across sessions. The transcript-upload and self-updater features create a real capability risk, so this should be warned rather than blocked.
Decision evidence
public snapshot- Explicit setup enables global agent guidance, skills, and lifecycle hooks by default.
- The hook installer writes commands into Codex and Claude agent hook configuration.
- The local HUD reads an active session transcript and can upload its full content to the EchoMem service.
- The runtime updater installs another release of this package, although it disables npm lifecycle scripts.
- No npm install lifecycle hook is declared, so these actions do not run merely on package installation.
- Configuration and hook writes require an explicit setup, init, or update command.
- The staged runtime install uses --ignore-scripts.
- No evidence of shell-obfuscated payloads, credential harvesting, or arbitrary external command execution was found.
Source & flagged code
9 flaggedPackage source references child process execution.
dist/durable-entry.jsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @echomem/mcp@1.4.52.
See all versions of @echomem/mcp for other recorded verdicts.
- Review the evidence and your use of @echomem/mcp@1.4.52 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.