Waxell
Multi-agent collaboration plugin for Claude Code. Spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any problem that benefits from diverse solutions. Evaluate by metric or LLM judge, merge the winner. 7 slash commands, agent templates, git DAG orchestration, message board coordination.
alirezarezvani's own description, from the plugin's files.
Stars
29,893
Version
v2
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 21 findings, highest severity high.

Highest severity
high
Findings
21
What ran
Static analysis + deep scan

A clean result means nothing alarming in what is published, not a guarantee. How the checks work

We don't republish the plugin's instructions. Read them on GitHub at the reviewed commit.

Security

Security scan

Checked 2 days ago

Result

High risk Waxell rates it high risk: 21 findings, highest severity high.

Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work

Findings (21)

high · 7

  • high

    Tool Misuse: Tool Parameter Abuse

    agents/hub-coordinator.md:5 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    agents/hub-coordinator.md:5 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    agents/hub-coordinator.md:5 · skillspector:TM1

  • high

    Rogue Agent: Self-Modification

    skills/agenthub/SKILL.md:256 · skillspector:RA1

  • high

    Tool Misuse: Tool Parameter Abuse

    skills/agenthub/references/dag-patterns.md:142 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    skills/agenthub/scripts/result_ranker.py:84 · skillspector:TM1

  • high

    Memory Poisoning: Memory Manipulation

    skills/merge/SKILL.md:85 · skillspector:MP3

medium · 14

  • medium

    Bundled lifecycle hooks can run automatically when their configured events occur, so their reach and handler capability

    hooks/hooks.json:1 · skillspector:BH1

  • medium

    Dangerous Code Execution: subprocess module call

    skills/agenthub/scripts/dag_analyzer.py:26 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    skills/agenthub/scripts/result_ranker.py:27 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    skills/agenthub/scripts/session_manager.py:72 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    skills/agenthub/scripts/dag_analyzer.py:100 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    skills/agenthub/scripts/dry_run.py:205 · skillspector:AST4

  • medium

    Agent Snooping: Skill Enumeration

    skills/agenthub/scripts/dry_run.py:256 · skillspector:AS3

  • medium

    Agent Snooping: Skill Enumeration

    skills/agenthub/scripts/dry_run.py:257 · skillspector:AS3

  • medium

    Agent Snooping: Skill Enumeration

    skills/agenthub/scripts/dry_run.py:258 · skillspector:AS3

  • medium

    Agent Snooping: Skill Enumeration

    skills/agenthub/scripts/dry_run.py:259 · skillspector:AS3

  • medium

    Agent Snooping: Skill Enumeration

    skills/agenthub/scripts/dry_run.py:260 · skillspector:AS3

  • medium

    Dangerous Code Execution: subprocess module call

    skills/agenthub/scripts/result_ranker.py:84 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    skills/agenthub/scripts/session_manager.py:201 · skillspector:AST4

  • medium

    Excessive Agency: Autonomous Decision Making

    skills/hub-run/SKILL.md:110 · skillspector:EA2

Versions

Version history

Each distinct content we have seen, newest first, with the verdict it got at the time.

  1. v2 (2.14.11)2026-11-163 added, 2 changed High riskgot riskier
  2. v1 (2.14.7)2026-11-03 No issues

Files

Files

25 files, 128 KB in total. Names only; open them on GitHub.

  • .claude-plugin/plugin.json
  • CLAUDE.md
  • README.md
  • agents/hub-coordinator.md
  • hooks/hooks.json
  • hooks/skill_router.py
  • hooks/skill_routes.json
  • settings.json
  • skills/agenthub/SKILL.md
  • skills/agenthub/references/agent-templates.md
  • skills/agenthub/references/coordination-strategies.md
  • skills/agenthub/references/dag-patterns.md
  • skills/agenthub/scripts/board_manager.py
  • skills/agenthub/scripts/dag_analyzer.py
  • skills/agenthub/scripts/dry_run.py
  • skills/agenthub/scripts/hub_init.py
  • skills/agenthub/scripts/result_ranker.py
  • skills/agenthub/scripts/session_manager.py
  • skills/board/SKILL.md
  • skills/eval/SKILL.md
  • skills/hub-init/SKILL.md
  • skills/hub-run/SKILL.md
  • skills/hub-status/SKILL.md
  • skills/merge/SKILL.md
  • skills/spawn/SKILL.md

See and control which skills your people use

Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.

30 minutes. No commitment.

SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF

More engineering skills and plugins

See all