Waxell

skill

gstack-upgrade High risk

garrytangarrytan/gstackupdated

Upgrade gstack to the latest version. Use for: upgrade gstack, update gstack version.
garrytan's own description, from the skill's files.
Otherskill
Stars
142,230
Version
v1
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 49 findings, highest severity critical.

Highest severity
critical
Findings
49
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 skill'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: 49 findings, highest severity critical.

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 (49)

critical · 2

  • critical

    Tells Claude to download a script and pipe it to a shell

    SKILL.md:178 · skill_risk:S1

  • critical

    Tells Claude to download a script and pipe it to a shell

    SKILL.md.tmpl:184 · skill_risk:S1

high · 21

  • high

    Supply Chain: External Script Fetching

    SKILL.md:178 · skillspector:SC2

  • high

    Supply Chain: External Script Fetching

    SKILL.md.tmpl:184 · skillspector:SC2

  • high

    Tool Misuse: Tool Parameter Abuse

    SKILL.md:181 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    SKILL.md:202 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    SKILL.md.tmpl:187 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    SKILL.md.tmpl:208 · skillspector:TM1

  • high

    analysis-evasion: Incomplete referenced artifact analysis

    SKILL.md:200 · skillspector:AE1

  • high

    Tool Misuse: Chaining Abuse

    SKILL.md:216 · skillspector:TM2

  • high

    Tool Misuse: Chaining Abuse

    SKILL.md.tmpl:222 · skillspector:TM2

  • high

    Agent Snooping: Agent Config Directory Access

    SKILL.md:262 · skillspector:AS1

  • high

    Agent Snooping: Agent Config Directory Access

    SKILL.md.tmpl:268 · skillspector:AS1

  • high

    Tool Misuse: Tool Parameter Abuse

    SKILL.md:275 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    SKILL.md.tmpl:281 · skillspector:TM1

  • high

    Tool Misuse: Chaining Abuse

    SKILL.md:275 · skillspector:TM2

  • high

    Tool Misuse: Chaining Abuse

    SKILL.md.tmpl:281 · skillspector:TM2

  • high

    Tool Misuse: Chaining Abuse

    migrations/v1.38.1.0.sh:49 · skillspector:TM2

  • high

    Tool Misuse: Tool Parameter Abuse

    SKILL.md:356 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    SKILL.md.tmpl:362 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    SKILL.md:357 · skillspector:TM1

  • high

    Tool Misuse: Tool Parameter Abuse

    SKILL.md.tmpl:363 · skillspector:TM1

  • high

    Prompt Injection: Exfiltration Commands

    migrations/v1.27.0.0.sh:416 · skillspector:P3

medium · 26

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:12 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:49 · skillspector:RA2

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md:188 · skillspector:EA2

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md.tmpl:194 · skillspector:EA2

  • medium

    Agent Snooping: Skill Enumeration

    SKILL.md:301 · skillspector:AS3

  • medium

    Agent Snooping: Skill Enumeration

    SKILL.md.tmpl:307 · skillspector:AS3

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:350 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md.tmpl:356 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md.tmpl:20 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md.tmpl:55 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.27.0.0.sh:8 · skillspector:RA2

  • medium

    Privilege Escalation: Sudo/Root Execution

    migrations/v1.27.0.0.sh:122 · skillspector:PE2

  • medium

    Privilege Escalation: Sudo/Root Execution

    migrations/v1.27.0.0.sh:313 · skillspector:PE2

  • medium

    Privilege Escalation: Sudo/Root Execution

    migrations/v1.91.19.0.sh:44 · skillspector:PE2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.27.0.0.sh:337 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.65.0.0.sh:6 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.65.0.0.sh:28 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.65.0.0.sh:50 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.65.0.0.sh:67 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.65.0.0.sh:68 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.65.0.0.sh:69 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.65.0.0.sh:70 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.65.0.0.sh:91 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.65.0.0.sh:91 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.65.0.0.sh:95 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    migrations/v1.65.0.0.sh:95 · skillspector:RA2

Versions

Version history

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

One version so far: v1 (1.1.0), seen 2026-11-19.

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 other skills and plugins

See all