@echomem/mcp@1.4.42
EchoMem MCP bridge: cloud-first memory tools and the Agent Doctor workspace forensics report (cost ledger + 3D repo city)
AI Security Review
scanned 3mo ago · by lpm-firewall-aiSource confirms a persistent, behavior-bearing AI-agent integration with coercive default-memory guidance. Its explicit CLI trigger and absence of install lifecycle hooks make this a warning rather than a publish-blocking malicious package.
Decision evidence
public snapshot- `setup` writes global agent guidance selecting EchoMem as the default memory provider and requiring saves without a separate request.
- The default `setup` path installs that guidance, bundled skills, and lifecycle hooks.
- Installed Codex hooks execute package commands on SessionStart and Stop.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The mutations are reached through explicit `init`/`setup` CLI subcommands, not package installation.
- The source scopes its config edits to EchoMem-owned entries and supports opt-out flags.
Source & flagged code
10 flaggedPackage source references dynamic require/import behavior.
dist/headless-runtime.jsView on unpkg · L65Findings
Affected versions and remediation
This report applies to @echomem/mcp@1.4.42.
See all versions of @echomem/mcp for other recorded verdicts.
- Review the evidence and your use of @echomem/mcp@1.4.42 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.