MCP Registry

guardvibe

by goklab
b4f7d462-26f8-5039-886f-5c9b3c2de0f0 | Store v3.81.0
100/ 100
CRITICAL risk
No change since v3.80.0
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
v3.81.0
Artifact
SHA256 9ab89d94…ab99ba
Detail
Full list

Evidence ledger

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

540 findings
Showing 25 of 67 · highest severity first

YARA Rule Matches

28 rules
SeverityRuleHitsFilesMetadata
HIGHAllowingRequestsWithExcessiveContentLengthSecurity

Rejecting requests with significant content length is a good practice to control the network traffic intensity and thus resource consumption in order to prevents DoS attacks, In your multer by default is no limit and maximum accept in Formidable and multer is 8mb. Ask Yourself Whether: Size limits are not defined for the different resources of the web application? The web application is not protected by rate limiting features? The web application infrastructure has limited resources? There is a risk if you answered yes to any of those questions. For more information checkout the CWE-770 (https://cwe.mitre.org/data/definitions/770.html) advisory.

1
build/data/rules/cve-versions.js
FP 15%
LOWNoUseEval 2
build/tools/taint-analysis.jsbuild/tools/cross-file-taint.js
-
LOWpostinstall file download 45
build/data/rules/web-security.jsbuild/data/compliance-metadata.jsbuild/utils/osv-client.js +42 more
-
LOWNoUseWeakRandom 4
build/data/rules/cve-versions.jsCHANGELOG.mdbuild/tools/check-code.js +1 more
-
LOWcredential git credentials 1
build/data/rules/supply-chain.js
-
LOWHavingAPermissiveCrossOriginResourceSharingPolicy 4
CHANGELOG.mdbuild/data/framework-guides.jsbuild/data/rules/modern-stack.js +1 more
-
LOWSQLInjection 3
build/tools/check-command.jsCHANGELOG.mdbuild/tools/taint-analysis.js
-
LOWServerHostnameNotVerified 2
CHANGELOG.mdbuild/data/rules/cve-versions.js
-
LOWcredential ssh keys 2
build/data/rules/ai-security.jsbuild/data/rules/cve-versions.js
-
LOWUsingCommandLineArguments 3
build/cli.jsbuild/cli/scan.jsbuild/index.js
-
LOWpostinstall obfuscation 30
build/data/rules/deployment.jsbuild/tools/scan-hallucinated.jsbuild/data/rules/ai-security.js +27 more
-
LOWpostinstall system command 78
build/utils/manifest-parser.jsbuild/tools/secure-prompt.jsbuild/tools/explain-remediation.js +75 more
-
LOWcredential aws credentials 2
build/data/rules/ai-tool-runtime.jsbuild/data/rules/cve-versions.js
-
LOWcredential postgres credentials 1
build/data/rules/shell.js
-
LOWpostinstall crypto operations 42
build/utils/typosquat.jsbuild/data/rules/go.jsbuild/data/compliance-metadata.js +39 more
-
LOWNoRenderContentFromRequest 1
build/data/rules/web-security.js
-
LOWUsingShellInterpreterWhenExecutingOSCommands 12
build/tools/taint-analysis.jsbuild/tools/review-pr.jsbuild/tools/scan-staged.js +9 more
-
LOWpostinstall registry modification 20
build/cli/audit.jsbuild/tools/check-package-health.d.tsbuild/utils/update-check.js +17 more
-
LOWpostinstall network communication 32
build/data/rules/ai-security.jsbuild/tools/check-code.jsbuild/data/rules/services.js +29 more
-
LOWpostinstall environment access 60
build/tools/export-sarif.d.tsbuild/tools/check-code.d.tsbuild/tools/scan-secrets.js +57 more
-
LOWpostinstall file manipulation 57
build/cli/audit.jsbuild/tools/explain-remediation.jsCHANGELOG.md +54 more
-
LOWcredential env files 44
build/tools/scan-host-config.d.tsbuild/tools/audit-config.jsbuild/data/rules/supply-chain.js +41 more
-
LOWpostinstall persistence mechanism 15
build/tools/check-command.jsREADME.mdbuild/data/rules/advanced-security.js +12 more
-
LOWRedirectToUnknownPath 4
build/data/framework-guides.jsbuild/data/rules/nextjs.jsbuild/tools/fix-code.js +1 more
-
LOWNoDisableTlsRejectUnauthorized 2
build/data/rules/advanced-security.jsbuild/data/rules/ai-tool-runtime.js
-
LOWcredential vscode credentials 1
build/cli/remediation.js
-
LOWServerCertificatesNotVerified 4
CHANGELOG.mdbuild/data/rules/advanced-security.jsbuild/data/rules/cve-versions.js +1 more
-
LOWpackage json suspicious scripts 1
build/data/rules/supply-chain.js
-

Network Indicators

Concrete URLs, domains, IPs, emails, and hashes extracted from the analyzed artifact.

92 total

Loading network indicators

Long lists can take a few seconds.

Finding Categories

1
Malware Signatures
10
Secrets
41
Network
92
IoC Indicators

YARA Rules Matched

28 rules(473 hits)
AllowingRequestsWithExcessiveContentLengthSecurity NoUseEval postinstall file download NoUseWeakRandom credential git credentials HavingAPermissiveCrossOriginResourceSharingPolicy SQLInjection ServerHostnameNotVerified credential ssh keys UsingCommandLineArguments postinstall obfuscation postinstall system command credential aws credentials credential postgres credentials postinstall crypto operations NoRenderContentFromRequest +12 more

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 tool poisoning; evidence quality moderate.

Jev rated 8 findings against the supplied code: 0 likely real, 1 likely benign pattern matches. The finding list was truncated; findings beyond it were not rated.

Key Reasons

  • MCP-TOOL-TOOL-POISONING-build/data/rules/ai-tool-runtime.js-121 (build/data/rules/ai-tool-runtime.js:121)
  • MCP-TOOL-TOOL-POISONING-build/data/rules/ai-security.js-399 (build/data/rules/ai-security.js:399)
  • MCP-TOOL-TOOL-POISONING-build/data/rules/ai-security.js-396 (build/data/rules/ai-security.js:396)

False Positive Considerations

  • MCP-TRANSPORT-HARDCODED-TOKEN-build/data/rules/core.js (build/data/rules/core.js)

Reviewed 2026-11-22 · version 3.81.0; recommended action: runtime analysis; model confidence 47%.

MCP version history

Risk trend by version

64 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
+15
Change from previous
No change
Versions:
First analyzed version
3.0.26
First seen Apr 26, 2026
Risk range
75 to 100
Across analyzed versions
Latest analyzed version
3.81.0
First seen Nov 21, 2026
Selected version
critical
Version
v3.81.0
First seen Yesterday
Risk score
100
Findings
632
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

Security infrastructure your AI can't be — deterministic, current past your model's training cutoff, whole-repo-aware, author-independent. Security MCP for vibe coding. 684 rules, 39 tools, CLI + doctor. Prompt-level shift-left security (secure_prompt — e

Frequently Asked Questions