keyring-agent-core@0.3.19
Core AI chat agent with multi-agent architecture, ReAct pattern, and modular tool system powered by Gemini
AI Security Review
scanned 23d ago · by lpm-firewall-aiInspected entrypoints support the package's AI and wallet functionality without a concrete malicious execution chain. Caller-supplied authentication and stubbed native filesystem helpers do not establish credential harvesting or install-time mutation.
Decision evidence
public snapshot- package.json has no registry install lifecycle hooks or runtime self-dependency.
- The native Gemini provider takes its API key and optional endpoint from caller configuration.
- Gemini requests send caller-supplied credentials with chat content through the configured client.
- Wallet action tools construct interface components from action parameters.
- Bundled native filesystem adapters reference empty module stubs rather than working filesystem imports.
Source & flagged code
4 flagged · loading sourceA single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/index.native.jsView on unpkg · L684Source reaches cloud instance metadata or link-local credential endpoints.
dist/index.native.jsView on unpkg · L1Findings
Affected versions and remediation
This report applies to keyring-agent-core@0.3.19.
See all versions of keyring-agent-core for other recorded verdicts.
- Review the evidence and your use of keyring-agent-core@0.3.19 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.