MCP Registry

@akasecurity/ai-tc-claude-code

3da33cbb-2111-59b0-8278-85e693a46c48 | v0.9.13
100/ 100
CRITICAL risk
No change since v0.9.7
Risk verdict
Do not install

Score-based assessment (critical risk, 100/100). No analyst review available.

Analysis record

Analysed
1 weeks ago
Version
v0.9.13
Artifact
SHA256 2DC…1B4
Source
Findings (non-IoC)

Evidence ledger

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

445 detail rows
Showing 25 of 136 · highest severity first

YARA Rule Matches

15 rules
SeverityRuleHitsFilesMetadata
LOWcredential env files 22
scripts/stop.jsscripts/query.jsscripts/dashboard.js +19 more
-
LOWpostinstall persistence mechanism 7
scripts/backfill.jsscripts/user-prompt-submit.jsscripts/pre-tool-use.js +4 more
-
LOWpostinstall file download 26
scripts/session-start.jsscripts/message-display.jsscripts/start-light.js +23 more
-
LOWHavingAPermissiveCrossOriginResourceSharingPolicy 15
scripts/query.jsscripts/firstrun.jsscripts/backfill.js +12 more
-
LOWNoUseWeakRandom 23
scripts/apply-suppressions.jsscripts/firstrun.jsscripts/onboard.js +20 more
-
LOWNoUseEval 15
scripts/remediate.jsscripts/apply-suppressions.jsscripts/filescan.js +12 more
-
LOWcredential ssh keys 15
scripts/reconcile.jsscripts/apply-suppressions.jsscripts/remediate.js +12 more
-
LOWUsingCommandLineArguments 1
scripts/dashboard.js
-
LOWpostinstall system command 38
commands/setup.mdcommands/audit.mdcommands/scan.md +35 more
-
LOWUsingShellInterpreterWhenExecutingOSCommands 23
scripts/sync.jsscripts/backfill.jsscripts/onboard.js +20 more
-
LOWpostinstall obfuscation 24
scripts/sync.jsscripts/post-model-switch.jsscripts/backfill.js +21 more
-
LOWpostinstall file manipulation 24
scripts/intro.jsscripts/post-tool-use.jsscripts/statusline.js +21 more
-
LOWpostinstall registry modification 25
scripts/backfill.jsscripts/session-start.jscommands/setup.md +22 more
-
LOWpostinstall network communication 25
scripts/remediate.jsscripts/backfill.jsscripts/session-start.js +22 more
-
LOWpostinstall crypto operations 26
scripts/session-start.jscommands/setup.mdscripts/backfill.js +23 more
-

Network Indicators

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

172 total
...

Network indicators are queued for lazy loading

Scroll this section into view to load the detailed rows.

Finding Categories

75
Secrets
23
Obfuscation
38
Network
172
IoC Indicators

YARA Rules Matched

15 rules(309 hits)
credential env files postinstall persistence mechanism postinstall file download HavingAPermissiveCrossOriginResourceSharingPolicy NoUseWeakRandom NoUseEval credential ssh keys UsingCommandLineArguments postinstall system command UsingShellInterpreterWhenExecutingOSCommands postinstall obfuscation postinstall file manipulation postinstall registry modification postinstall network communication postinstall crypto operations

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.

Security Analysis Summary

Security Analysis Overview

@akasecurity/ai-tc-claude-code is a MCP Servers extension published by GitHub Actions. Version 0.9.13 has been analyzed by the Risky Plugins security platform, receiving a risk score of 100/100 (CRITICAL risk) based on 617 security findings.

Risk Assessment

This extension presents critical security risk. Severe issues were detected, potentially including malware indicators, exposed secrets, or dangerous behaviors. Installation is strongly discouraged until these issues are addressed.

Findings Breakdown

  • Critical: 75 finding(s)
  • High: 23 finding(s)
  • Medium: 210 finding(s)
  • Low: 309 finding(s)

What Was Analyzed

The security assessment covers multiple analysis categories:

  • Malware Detection: YARA rule matching against 2,400+ malware signatures
  • Secret Detection: Scanning for exposed API keys, tokens, and credentials
  • Static Analysis: Code-level security analysis for common vulnerability patterns
  • Network Analysis: Detection of suspicious network communications and endpoints
  • Obfuscation Detection: Identification of code obfuscation techniques

Developer Information

@akasecurity/ai-tc-claude-code is published by GitHub Actions on the MCP Servers marketplace.

Recommendation

This extension is not recommended for installation without thorough manual review. Consider alternatives with lower risk scores, or contact the developer to address the identified security concerns.

MCP version history

Risk trend by version

3 analyzed versions. Each point is the latest successful scan for that version; failed zero-score scans are hidden. Dates are based on first seen by risky plugins.

Selected
100
Change since first
No change
Change from previous
No change
Versions:
First analyzed version
0.9.6
Aug 17, 2026
Risk range
100 to 100
Across analyzed versions
Latest analyzed version
0.9.13
Sep 22, 2026
Selected version
critical
Version
v0.9.13
1 weeks ago
Risk score
100
Findings
618
Change vs previous
No change

Pick any point on the chart to explore that version's code below.

About This Extension

AI Traffic Control — inspect and govern AI prompts in Claude Code

Frequently Asked Questions