@mnemom/mnemom@0.17.2
Transparent AI agent tracing
AI Security Review
scanned 12d ago · by lpm-firewall-aiInspected source shows no install-time execution or concrete attack behavior. The flagged process, network, and file operations are gated CLI functions consistent with the package's user-invoked behavior.
Decision evidence
public snapshot- package.json defines only a prepublishOnly build lifecycle hook.
- The automatic version upgrade requires auto mode and a supported install method.
- The proxy adds Mnemom routing headers to gateway requests.
- The agent command writes temporary MCP configuration without embedding key material.
- Goal commands use a caller-selected URL for their fetch operation.
Source & flagged code
5 flagged · loading sourcePackage source references child process execution.
dist/lib/update/min-version.jsView on unpkg · L6A single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/rc-proxy.mjsView on unpkg · L76Findings
Affected versions and remediation
This report applies to @mnemom/mnemom@0.17.2.
See all versions of @mnemom/mnemom for other recorded verdicts.
- Review the evidence and your use of @mnemom/mnemom@0.17.2 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.