MCP Registry

@agent-infra/mcp-shared

569bee3e-9df1-5dcd-afdc-8402464e5c54 | Store v1.2.29
33/ 100
LOW risk
Risk verdict
No high-risk signal observed

Score-based assessment (low risk, 33/100). An AI review is available in the AI review tab.

Analysis record

Analysed
7 months ago 19 April 2026
Version
v1.2.29
Artifact
SHA256 ccff3da3…15a10f
Detail
Full list

Evidence ledger

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

5 findings

YARA Rule Matches

2 rules
SeverityRuleHitsFilesMetadata
HIGHpostinstall system command

System command execution detected

1
LICENSE
Risky Plugins Authors FP 10%
HIGHpostinstall file download

File download activity detected

1
package.json
Risky Plugins Authors FP 30%

Finding Categories

2
Malware Signatures
7
IoC Indicators

YARA Rules Matched

2 rules
postinstall system command postinstall file download

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 appears to be a false positive driven by artifact noise rather than malicious behavior. The high risk score (73.65) stems entirely from 10 IoC findings and 2 legacy malware-signature hits, which are common false positives in bundled/minified JavaScript environments. Crucially, the scan detected zero network findings, zero tool-poisoning findings, and zero code-smell issues. The absence of network findings is a strong negative signal against data exfiltration, and the lack of tool-poisoning findings rules out the primary MCP attack vector. The 'malware-signature' findings likely match generic byte patterns or packed code in dependencies rather than active payloads. Without evidence of credential harvesting, hidden directives, or suspicious network destinations, this package poses no apparent threat beyond being an unpublished/unused artifact (0 users).

Key Reasons

  • Zero tool-poisoning findings detected
  • Zero network findings detected (rules out exfiltration)
  • Findings limited to IoC noise and legacy YARA signatures
  • Package has 0 active users

False Positive Considerations

  • Legacy YARA malware-signature rules matching packed/bundled code
  • IoC extractor flagging generic infrastructure domains or embedded data
  • No actual behavioral telemetry (network/execution) to support high score

Reviewed 2026-04-12; recommended action: suppress false positive; model confidence 55%.

Source Code Viewer

Source Code Not Available

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

About This Extension

MCP shared

Frequently Asked Questions