Score-based assessment (medium risk, 49/100). Last analyst review covers version unknown.
Analysis record
- Analysed
- 6 months ago
- Version
- v1.0.1
- Artifact
- SHA256 AD8…EF6
- Source
- Findings (non-IoC)
Evidence ledger
Ranked by severity · findings with a source location link to the code viewer
YARA Rule Matches
5 rules| Severity | Rule | Hits | Files | Metadata |
|---|---|---|---|---|
| HIGH | postinstall network communication Network communication detected | 2 | LICENSEdist/index.js | Risky Plugins Authors FP 30% |
| HIGH | postinstall environment access Environment variable access detected | 1 | dist/api/types.d.ts | Risky Plugins Authors FP 40% |
| HIGH | postinstall system command System command execution detected | 3 | dist/api/rate-limiter.d.tsdist/api/client.jsREADME.md | Risky Plugins Authors FP 10% |
| HIGH | postinstall file download File download activity detected | 1 | dist/api/client.js | Risky Plugins Authors FP 30% |
| HIGH | credential env files Environment configuration file path detected | 1 | dist/api/client.js | Risky Plugins Authors FP 10% |
Finding Categories
YARA Rules Matched
5 rules(8 hits)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 none; evidence quality weak.
This package presents a high risk score (83.19) primarily due to indicator volume (21 IoCs) and legacy YARA matches, rather than confirmed malicious behavior.
Tool Poisoning Assessment: The findings summary explicitly lists 0 tool-poisoning detections. This is a strong indicator that the package does not contain hidden directives aimed at manipulating the AI agent.
Credential & Network Scope: There are no findings related to secret scanning, credential access, or environment variable exfiltration. The single network finding and the bulk of IoC detections are characteristic of standard library dependencies (e.g., calls to Semantic Scholar APIs or CDNs) or minified code artifacts.
Malware Signatures: The 8 malware-signature findings are likely false positives from broad YARA rules matching common code patterns in bundled node_modules or dist files, as there is no corresponding secret or credential-theft signal to support a malicious verdict.
Given the absence of tool poisoning, credential harvesting, or data exfiltration architecture, this appears to be a benign package inflated by scanner noise.
Key Reasons
- Zero tool-poisoning findings despite high risk score
- No credential access or secret harvesting findings
- IoC and malware-signature counts consistent with bundled dependency noise
- No file-level evidence provided to support generic YARA matches
False Positive Considerations
- IoC Extractor Garbage (ubiquitous domains in dependencies)
- YARA Code-Smell Rules (broad malware-family matches in dist files)
- Score Inflation (high volume of low-severity matches)
Reviewed 2026-04-13; recommended action: suppress false positive; model confidence 82%.
Source Code Not Available
Source code is not available for this version of the extension.
About This Extension
Frequently Asked Questions
Similar Extensions
Related extensions from the same publisher or marketplace