keyring-agent-core@0.3.14
Core AI chat agent with multi-agent architecture, ReAct pattern, and modular tool system powered by Gemini
AI Security Review
scanned 25d ago · by lpm-firewall-aiStatic inspection found no lifecycle hook or concrete malicious behavior. Network use is consistent with the package's chat-agent function and occurs through configured or fixed Gemini endpoints.
Decision evidence
public snapshot- The manifest defines build and development scripts but no install lifecycle hook.
- The native entrypoint selects either a caller-provided Gemini API endpoint or a fixed Keyring Gemini proxy.
- Chat requests are made through the selected model endpoint when the caller invokes chat.
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 · L681Source 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@0.3.14.
See all versions of keyring-agent-core for other recorded verdicts.
- Review the evidence and your use of keyring-agent-core@0.3.14 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.