keyring-agent-core@0.3.6
Core AI chat agent with multi-agent architecture, ReAct pattern, and modular tool system powered by Gemini
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe source establishes a real remote-data capability backed by a bundled credential, but it is opt-in and no concrete malware or install-time attack was found. A warning is appropriate until the credential is removed and consumers are required to configure their own endpoint.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
A consumer enables vectorKB and invokes knowledge-base search, ingestion, or maintenance methods.
Impact
Knowledge-base content may leave the consumer environment, and the bundled service credential may be misused to access or modify its vector store.
Mechanism
Remote vector database client with bundled default endpoint and credential fallback.
AI rationale
The source establishes a real remote-data capability backed by a bundled credential, but it is opt-in and no concrete malware or install-time attack was found. A warning is appropriate until the credential is removed and consumers are required to configure their own endpoint.
Evidence
dist/index.js
Network endpoints1
perfect-octopus-59684-us1-vector.upstash.io
Decision evidence
public snapshotAI called this Suspicious at 86.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- The Node bundle embeds a default Upstash vector-service endpoint and falls back to a bundled token when callers do not supply one.
- When vector knowledge-base mode is enabled, the package sends knowledge-base queries to that remote service and exposes write and reset operations through the same client.
Evidence against
- The only lifecycle hook is prepublishOnly, so registry installation does not run package code.
- The remote vector feature is gated by the caller's vectorKB.enabled option.
- No child-process execution, dynamic code execution, metadata access, or install-time persistence was confirmed.
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 one=Object.create;var Xg=Object.defineProperty;var ane=Object.getOwnPropertyDescriptor;var sne=Object.getOwnPropertyNames;var lne=Object.getPrototypeOf,cne=Object....
L3:
L4: Troubleshooting URL: https://docs.langchain.com/oss/javascript/langgraph/${r.lc_error_code}/
L5: `);super(n);h(this,"lc_error_code");this.lc_error_code=r?.lc_error_code}},kR=class extends Bo{get is_bubble_up(){return!0}},que=class extends Bo{constructor(t,e){super(t,e),this.na...
L6:
L7: Troubleshooting URL: https://docs.langchain.[redacted]/${e}/
L8: `,t}var C_=dhe.ns.sub("error"),LT=class extends C_.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@0.3.6.
See all versions of keyring-agent-core for other recorded verdicts.
- Review the evidence and your use of keyring-agent-core@0.3.6 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.