MCP Registry

@event4u/agent-config

3ae77a99-85bf-5c17-ba20-f14dade0f53e | Store v20.6.0
100/ 100
CRITICAL risk
No change since v20.5.0
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 20 November 2026
Version
v20.6.0
Artifact
SHA256 f57ee18b…b2aff6
Detail
Partial list

Evidence ledger

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

Showing 1,000 of 9,438 findings.
Showing 25 of 49 · highest severity first

YARA Rule Matches

15 rules
SeverityRuleHitsFilesMetadata
LOWUsingCommandLineArguments 429
src/scripts/routing_arms.tssrc/scripts/lint_agent_security.tssrc/scripts/plan_test_shards.ts +426 more
-
LOWNoWriteOnDocumentContentFromRequest 1
src/scripts/runtime_dispatcher.ts
-
LOWLocalStorageShouldNotBeUsed 3
dist/agent-src/skills/html-deck/templates/deck-shell.htmldist/agent-src/skills/design-intelligence/data/stacks/angular.csvdist/ui/assets/index-0I6g16Ha.js
-
LOWDebuggerStatementsShouldNotBeUsed 22
docs/guidelines/agent-infra/agent-interaction-and-decision-quality.mddist/agent-src/guidelines/php/general.mddist/agent-src/skills/php-debugging/SKILL.md +19 more
-
LOWcredential ssh keys 4
dist/install/deployCopy.jssrc/install/deployCopy.tsdist/agent-src/guidelines/agent-infra/untrusted-input-spotlighting.md +1 more
-
LOWcredential aws profile 1
dist/agent-src/skills/terragrunt/SKILL.md
-
LOWpostinstall file download 439
dist/hooks/web_launch_rows.chunk.cjsdist/agent-src/commands/project/map.mdsrc/config/startup-contract-clauses.json +436 more
-
LOWNoUseWeakRandom 22
src/scripts/retro_queue.tssrc/scripts/_lib/switch_relay.tsdist/cli-delegate/chunk-FULCXQI3.js +19 more
-
LOWNoUseEval 7
src/scripts/ui_conformance_probe.tssrc/scripts/skill_trigger_eval.tssrc/scripts/eval_ui_triviality.ts +4 more
-
LOWSQLInjection 2
src/scripts/memory_eviction.tssrc/scripts/_lib/schema/adapters/tbls.ts
-
LOWcredential gcp credentials 3
dist/hooks/dispatch.jssrc/scripts/_lib/credential_deny_rows.tssrc/scripts/_lib/credential_files.ts
-
LOWHavingAPermissiveCrossOriginResourceSharingPolicy 1
dist/agent-src/skills/frontend-render-security/SKILL.md
-
LOWcredential docker env 3
src/scripts/_lib/credential_files.tssrc/scripts/_lib/credential_deny_rows.tsdist/hooks/dispatch.js
-
LOWcredential git credentials 11
src/scripts/_lib/spawn_env.tsdist/mcp/server.mjsdist/cli-delegate/chunk-2RDQ6CZI.js +8 more
-
LOWcredential azure credentials 3
dist/hooks/dispatch.jssrc/scripts/_lib/credential_deny_rows.tssrc/scripts/_lib/credential_files.ts
-

Network Indicators

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

2,622 total

Loading network indicators

Long lists can take a few seconds.

Finding Categories

11
Secrets
3
Obfuscation
24
Network
2,622
IoC Indicators

YARA Rules Matched

15 rules(951 hits)
UsingCommandLineArguments NoWriteOnDocumentContentFromRequest LocalStorageShouldNotBeUsed DebuggerStatementsShouldNotBeUsed credential ssh keys credential aws profile postinstall file download NoUseWeakRandom NoUseEval SQLInjection credential gcp credentials HavingAPermissiveCrossOriginResourceSharingPolicy credential docker env credential git credentials credential azure credentials

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 credential theft; evidence quality moderate.

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/cli-delegate/chunk-5AYJGUA3.js (dist/cli-delegate/chunk-5AYJGUA3.js)
  • MCP-TRANSPORT-HARDCODED-TOKEN-dist/mcp/server.mjs (dist/mcp/server.mjs)
  • MCP-TRANSPORT-HARDCODED-TOKEN-dist/hooks/egress_engine.chunk.cjs (dist/hooks/egress_engine.chunk.cjs)

Reviewed 2026-11-20 · version 20.6.0; recommended action: runtime analysis; model confidence 44%.

MCP version history

Risk trend by version

7 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
20.0.0
First seen Nov 4, 2026
Risk range
100 to 100
Across analyzed versions
Latest analyzed version
20.6.0
First seen Nov 20, 2026
Selected version
critical
Version
v20.6.0
First seen Yesterday
Risk score
100
Findings
12060
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

Skills, rules, slash commands and subagents for Claude Code, Cursor, Copilot, Codex and more AI coding tools — teach your AI coding agents to check their work before they say done.

Frequently Asked Questions