registry / keyring-agent-core / 0.3.10
keyring-agent-core@0.3.10
Core AI chat agent with multi-agent architecture, ReAct pattern, and modular tool system powered by Gemini
AI Security Review
scanned 29d ago · by lpm-firewall-aiStatic inspection shows a Gemini multi-agent library whose entrypoints only export constructors and helpers. Install hooks, process execution, and covert exfiltration are absent, and the embedded vector default is used only when the caller enables that knowledge base.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
No automatic install or import trigger runs package code.
Impact
No unconsented mutation, credential harvest, or remote payload execution was found.
Mechanism
Consumers call exported agent and tool constructors. Network clients talk to configured DeFi, Gemini, and optional vector endpoints only after those calls.
AI rationale
Static inspection shows a Gemini multi-agent library whose entrypoints only export constructors and helpers. Install hooks, process execution, and covert exfiltration are absent, and the embedded vector default is used only when the caller enables that knowledge base.
Decision evidence
public snapshotAI called this Clean at 86.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json version 0.3.10 sets main to dist/index.js and react-native to dist/index.native.js, with scripts limited to build, lint, test, and prepublishOnly build and no preinstall, install, or postinstall hook.
- dist/index.js exports AgentCore and DeFi/wallet tools, creates an axios client, and does not spawn processes, eval code, or run network calls at module load.
- dist/index.native.js is the React Native bundle entry and contains no child_process usage or install-time execution.
Evidence against
- Both bundles fall back to a vendor Upstash Vector REST URL and token only when UpstashKnowledgeBase is constructed or AgentCore is given vectorKB.enabled.
Behavioral surface
EnvironmentVarsNetwork
HighEntropyStringsMinifiedPossibleObfuscationUrlStrings
Source & flagged code
5 flagged · loading sourcedist/index.native.jsView file
681L682: USER QUERY: ${e}`,timestamp:0}];try{let s=(await this.llm.chat(i)).text.trim().match(/\[[\s\S]*\]/);if(!s)return[];let l=JSON.parse(s[0]),c=[];for(let u of l)u.index>=0&&u.index<th...
L683:
High
Same File Env Network Execution
A single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/index.native.jsView on unpkg · L6811if(typeof Symbol!=="undefined"){if(!Symbol.asyncIterator){try{Symbol.asyncIterator=Symbol("Symbol.asyncIterator")}catch(e){}}if(!Symbol.asyncDispose){try{Symbol.asyncDispose=Symbol...
L2: "use strict";var Hne=Object.create;var gy=Object.defineProperty;var Zne=Object.getOwnPropertyDescriptor;var Gne=Object.getOwnPropertyNames;var Wne=Object.getPrototypeOf,Kne=Object....
L3:
L4: Troubleshooting URL: https://docs.langchain.com/oss/javascript/langgraph/${r.lc_error_code}/
L5: `);super(n);f(this,"lc_error_code");this.lc_error_code=r?.lc_error_code}},rN=class extends Xo{get is_bubble_up(){return!0}},zde=class extends Xo{constructor(t,e){super(t,e),this.na...
L6:
L7: Troubleshooting URL: https://docs.langchain.[redacted]/${e}/
L8: `,t}var W_=mfe.ns.sub("error"),pk=class extends W_.brand(Err
High
Cloud Metadata Access
Source reaches cloud instance metadata or link-local credential endpoints.
dist/index.native.jsView on unpkg · L1Findings
1 Critical4 High3 Medium4 Low
CriticalPrevious Version Dangerous Deltadist/index.js
HighSame File Env Network Executiondist/index.native.js
HighCloud Metadata Accessdist/index.native.js
HighObfuscated Payload Loaderdist/index.native.js
HighSemantic Analysis Limiteddist/index.native.js
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowNon Install Lifecycle Scripts
LowScripts Present
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to keyring-agent-core@0.3.10.
See all versions of keyring-agent-core for other recorded verdicts.
- Review the evidence and your use of keyring-agent-core@0.3.10 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.