MCP Registry

@furrow-cam/mcp

6f65852e-4a1a-5934-b3cd-35525bf7fff9 | Store v0.13.0
100/ 100
CRITICAL risk
No change since v0.12.0
Risk verdict
Do not install

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

Analysis record

Analysed
Yesterday 21 November 2026
Version
v0.13.0
Artifact
SHA256 ce35a8e3…e2009e
Detail
Full list

Evidence ledger

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

119 findings
Showing 25 of 92 · highest severity first

YARA Rule Matches

12 rules
SeverityRuleHitsFilesMetadata
LOWcredential env files 2
package.jsondist/main.js
-
LOWpostinstall persistence mechanism 4
fonts/Pacifico-Regular.ttfdist/main.jsfonts/JetBrainsMono-Regular.ttf +1 more
-
LOWpostinstall crypto operations 1
dist/main.js
-
LOWpostinstall system command 3
dist/THIRD-PARTY-NOTICES.txtREADME.mddist/main.js
-
LOWpostinstall network communication 4
LICENSEdist/THIRD-PARTY-NOTICES.txtREADME.md +1 more
-
LOWpostinstall obfuscation 1
dist/main.js
-
LOWpostinstall registry modification 1
dist/main.js
-
LOWpostinstall environment access 4
fonts/JetBrainsMono-OFL.txtfonts/Relief-OFL.txtfonts/Arvo-OFL.txt +1 more
-
LOWpostinstall file manipulation 3
fonts/JetBrainsMono-Regular.ttfREADME.mddist/main.js
-
LOWpostinstall file download 2
README.mddist/main.js
-
LOWSQLInjection 1
dist/main.js
-
LOWNoUseWeakRandom 1
dist/main.js
-

Finding Categories

86
Secrets
2
Network
652
IoC Indicators

YARA Rules Matched

12 rules(27 hits)
credential env files postinstall persistence mechanism postinstall crypto operations postinstall system command postinstall network communication postinstall obfuscation postinstall registry modification postinstall environment access postinstall file manipulation postinstall file download SQLInjection NoUseWeakRandom

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.

Jev rated 8 findings against the supplied code: 0 likely real, 0 likely benign pattern matches. The finding list was truncated; findings beyond it were not rated.

Key Reasons

  • MCP-TRANSPORT-HARDCODED-TOKEN-dist/main.js (dist/main.js)
  • MCP-TRANSPORT-HARDCODED-TOKEN-dist/main.js (dist/main.js)
  • MCP-TRANSPORT-HARDCODED-TOKEN-dist/main.js (dist/main.js)

Reviewed 2026-11-21 · version 0.13.0; recommended action: reanalyze; model confidence 64%.

MCP version history

Risk trend by version

8 analyzed versions. Each point is the latest successful scan for that version; failed zero-score scans are hidden. Dates: First seen by Risky Plugins.

Selected
100
Change since first
No change
Change from previous
No change
Versions:
First analyzed version
0.7.1
First seen Nov 9, 2026
Risk range
100 to 100
Across analyzed versions
Latest analyzed version
0.13.0
First seen Nov 21, 2026
Selected version
critical
Version
v0.13.0
First seen Yesterday
Risk score
100
Findings
771
Change vs previous
No change

Pick any point on the chart, then open the Source tab to read that version's code.

Source Code Viewer

Source Code Not Available

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

About This Extension

Furrow CAM's local MCP server: AI assistants work on .furrow projects over stdio (PRD-0012, ADR-0067)

Frequently Asked Questions