Waxell

skill

review High risk

garrytangarrytan/gstackupdated

Use when you review a diff before it lands: local changes, a branch or a PR. Use for: review my changes, look over my diff, review this pr. (gstack)
garrytan's own description, from the skill's files.
Otherskill
Stars
142,230
Version
v2
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 28 findings, highest severity high.

Highest severity
high
Findings
28
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 yesterday

Result

High risk Waxell rates it high risk: 28 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 (28)

high · 8

  • high

    Excessive Agency: External Model or Provider Selection

    SKILL.md:65 · skillspector:EA5

  • high

    Tool Misuse: Chaining Abuse

    SKILL.md:471 · skillspector:TM2

  • high

    Tool Misuse: Chaining Abuse

    greptile-triage.md:81 · skillspector:TM2

  • high

    Tool Misuse: Chaining Abuse

    greptile-triage.md:89 · skillspector:TM2

  • high

    System Prompt Leakage: Direct Prompt Extraction

    SKILL.md:576 · skillspector:P6

  • high

    System Prompt Leakage: Direct Prompt Extraction

    SKILL.md:590 · skillspector:P6

  • high

    Privilege Escalation: Credential Access

    specialists/security.md:39 · skillspector:PE3

  • high

    Tells Claude to install unpinned packages (@openai/codex)

    sections/adversarial.md:65 · skill_risk:S2

medium · 20

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:10 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:10 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:106 · skillspector:RA2

  • medium

    Privilege Escalation: Sudo/Root Execution

    SKILL.md:460 · skillspector:PE2

  • medium

    Privilege Escalation: Sudo/Root Execution

    greptile-triage.md:67 · skillspector:PE2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:512 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:630 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md.tmpl:210 · skillspector:RA2

  • medium

    Excessive Agency: Autonomous Decision Making

    checklist.md:153 · skillspector:EA2

  • medium

    Excessive Agency: Autonomous Decision Making

    checklist.md:211 · skillspector:EA2

  • medium

    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and pub

    design-checklist.md:25 · skillspector:RP1

  • medium

    Rogue Agent: Session Persistence

    design-checklist.md:76 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    greptile-triage.md:80 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    greptile-triage.md:88 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    sections/adversarial.md:248 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    sections/plan-completion.md:78 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    sections/preamble.md:22 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    sections/review-army.md:56 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    sections/review-army.md:114 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    specialists/testing.md:100 · skillspector:RA2

Versions

Version history

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

  1. v2 (1.0.0)2026-11-202 changed High risk
  2. v1 (1.0.0)2026-11-19 High risk

Files

Files

27 files, 268 KB in total. Names only; open them on GitHub.

  • SKILL.md
  • SKILL.md.tmpl
  • TODOS-format.md
  • checklist.md
  • design-checklist.md
  • gate-integrity.md
  • greptile-triage.md
  • sections/adversarial.md
  • sections/adversarial.md.tmpl
  • sections/manifest.json
  • sections/plan-completion.md
  • sections/plan-completion.md.tmpl
  • sections/preamble.md
  • sections/review-army.md
  • sections/review-army.md.tmpl
  • sections/shared-code-reuse.md
  • sections/shared-code-reuse.md.tmpl
  • specialists/api-contract.md
  • specialists/data-migration.md
  • specialists/maintainability.md
  • specialists/performance.md
  • specialists/red-team.md
  • specialists/security.md
  • specialists/simplification.md
  • specialists/state-machines.md
  • specialists/targeted.md
  • specialists/testing.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 other skills and plugins

See all