Waxell

skill

eval-plan High risk

garrytangarrytan/gstackupdated

Preregister a paid eval (bars, arms, decoys, stop rules), dry-run it at zero cost, then run a three-item priced pilot whose spend table gates approval. (gstack)
garrytan's own description, from the skill's files.
Stars
142,230
Version
v3
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 10 findings, highest severity high.

Highest severity
high
Findings
10
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 today

Result

High risk Waxell rates it high risk: 10 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 (10)

high · 1

  • high

    Excessive Agency: External Model or Provider Selection

    SKILL.md:39 · skillspector:EA5

medium · 9

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:16 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:16 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:80 · skillspector:RA2

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md:306 · skillspector:EA2

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md.tmpl:221 · skillspector:EA2

  • medium

    Privilege Escalation: Sudo/Root Execution

    SKILL.md:329 · skillspector:PE2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:356 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md.tmpl:264 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    sections/preamble.md:22 · skillspector:RA2

Versions

Version history

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

  1. v3 (1.0.0)2026-11-212 changed High risk
  2. v2 (1.0.0)2026-11-201 changed High risk
  3. v1 (1.0.0)2026-11-19 High risk

Files

Files

3 files, 64 KB in total. Names only; open them on GitHub.

  • SKILL.md
  • SKILL.md.tmpl
  • sections/preamble.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 productivity skills and plugins

See all