MCP Registry

@mseep/airylark-mcp-server

1c40468b-d5bb-510d-b918-38cf0c2f75eb | Store v0.1.0
64/ 100
MEDIUM risk
Risk verdict
Review before use

Score-based assessment (medium risk, 64/100). An AI review is available in the AI review tab.

Analysis record

Analysed
7 months ago 23 April 2026
Version
v0.1.0
Artifact
SHA256 30551236…97e94c
Detail
Full list

Evidence ledger

Ranked by severity · findings with a source location link to the code viewer

60 findings

YARA Rule Matches

8 rules
SeverityRuleHitsFilesMetadata
HIGHcredential env files

Environment configuration file path detected

6
README.mddist/index.jssrc/index.ts +3 more
Risky Plugins Authors FP 10%
HIGHpostinstall file download

File download activity detected

5
src/index.tssrc/text_eval.tsdist/text_eval.js +2 more
Risky Plugins Authors FP 30%
HIGHpostinstall obfuscation

Code obfuscation techniques detected

7
src/index.tssrc/text_eval.tsdist/text_eval.js.map +4 more
Risky Plugins Authors FP 20%
HIGHpostinstall network communication

Network communication detected

4
src/index.tsREADME.mddist/index.js +1 more
Risky Plugins Authors FP 30%
HIGHpostinstall system command

System command execution detected

6
dist/index.jssrc/index.tsREADME.md +3 more
Risky Plugins Authors FP 10%
HIGHpostinstall file manipulation

File system manipulation detected

2
dist/index.jssrc/index.ts
Risky Plugins Authors FP 20%
HIGHpostinstall environment access

Environment variable access detected

5
src/index.tssrc/text_eval.tsdist/text_eval.js +2 more
Risky Plugins Authors FP 40%
HIGHHavingAPermissiveCrossOriginResourceSharingPolicy

Same origin policy in browsers prevents, by default and for security-reasons, a javascript frontend to perform a cross-origin HTTP request to a resource that has a different origin (domain, protocol, or port) from its own. The requested target can append additional HTTP headers in response, called CORS, that act like directives for the browser and change the access control policy / relax the same origin policy. The Access-Control-Allow-Origin header should be set only for a trusted origin and for specific resources. For more information checkout the OWASP A6:2017 (https://owasp.org/www-project-top-ten/2017/A6_2017-Security_Misconfiguration.html) advisory.

2
src/index.tsdist/index.js
FP 10%

Finding Categories

37
Malware Signatures
2
Secrets
10
Network
22
IoC Indicators

YARA Rules Matched

8 rules(37 hits)
credential env files postinstall file download postinstall obfuscation postinstall network communication postinstall system command postinstall file manipulation postinstall environment access HavingAPermissiveCrossOriginResourceSharingPolicy

MCP Server Analysis

MCP servers expose tools and resources to AI assistants. Unlike browser extensions, they run as standalone processes with direct system access. Tool definitions are analyzed for prompt injection, data exfiltration, and tool poisoning patterns.

AI Security Report

AI Security Review

Evidence context: threat category unknown malware; evidence quality weak.

This package presents a critical risk score based primarily on a high volume of YARA malware signature matches (37) and IoCs (23). In the context of MCP triage, these findings are frequently false positives triggered by bundled dependencies in dist/ or minified JavaScript utilities. The absence of 'tool-poisoning' findings is a significant negative signal against this being an active MCP attack vector, as tool manipulation is the primary threat pattern for this ecosystem. However, the quantity of high-severity signatures (65) is atypical for a standard benign package and warrants verification to rule out a compromised supply chain or a malicious payload masquerading as a translation utility. The user count of zero further limits immediate exposure, but the technical indicators require a closer look at the specific files triggering the malware rules to confirm if this is a sophisticated threat or a scanner artifact.

Key Reasons

  • High risk score 100/CRITICAL generated by volume of YARA malware signatures (37)
  • Zero tool-poisoning findings detected, reducing likelihood of AI-manipulation
  • High IoC count (23) likely attributable to bundled dependencies or minified code
  • New/Zero-usage package with unverified publisher ('skydeckai')

False Positive Considerations

  • YARA malware signatures often misclassify minified JS or bundled node_modules as malicious
  • IoC counts in MCP packages are frequently inflated by CDN/generic infra domains
  • Lack of specific 'tool-poisoning' or 'credential-access' patterns suggests scanner noise

Reviewed 2026-04-12; recommended action: reanalyze; model confidence 60%.

Source Code Viewer

Source Code Not Available

Source code is not available for this version of the extension.

About This Extension

AiryLark的ModelContextProtocol(MCP)服务器,提供高精度翻译API

Frequently Asked Questions