@agent-infra/mcp-server-search
Score-based assessment (minimal risk, 0/100). An AI review is available in the AI review tab.
No individual score drivers were recorded for this analysis.
Analysis record
- Analysed
- 7 months ago 18 April 2026
- Version
- v1.2.29
- Detail
- Full list
No findings
The analyzer reported nothing for this version.
No findings
The analyzer reported nothing for this version.
AI Security Report
AI Security Review
Evidence context: threat category pup; evidence quality weak.
This package has a high automated risk score (79.92), but this appears to be a false positive driven by artifact noise rather than malicious behavior. The findings are entirely attributed to generic IoCs (10) and malware signatures (8) typically found in bundled node_modules or minified JavaScript. Critically for an MCP server, there are zero findings for 'tool-poisoning' or 'network' activity. This means there is no evidence of hidden AI manipulation directives (the defining MCP threat) or external network communication that would suggest data exfiltration. The 'malware-signature' hits are likely generic YARA matches on common library code patterns rather than actual payloads. Without tool poisoning, credential harvesting, or unknown network destinations, this package does not demonstrate the behavior patterns of a malicious MCP server.
Key Reasons
- Zero tool-poisoning findings despite high risk score
- Zero network findings (no exfiltration capability)
- IoC and malware-signature counts consistent with bundled dependencies
- No credential-access or secret findings
False Positive Considerations
- Bundled dependencies triggering generic IoC rules
- YARA malware signatures matching library code
Reviewed 2026-04-13; recommended action: suppress false positive; model confidence 60%.
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