Waxell

skill

axolotl High risk

orchestra-researchorchestra-research/ai-research-skillsupdated

Browse GitHub Download zipBook a demo
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
orchestra-research's own description, from the skill's files.
ResearchAI & agentsskill
Stars
14,234
Version
v1
Copies
0
OverviewSecurity12Versions1

Overview

blockHigh risk

Waxell rates it high risk: 12 findings, highest severity critical.

Highest severity
critical
Findings
12
What ran
Static analysis

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: 12 findings, highest severity critical.

Checked with static analysis: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. Nothing was run. How the checks work

Findings (12)

critical · 1

  • critical

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

    references/other.md:310 · skill_risk:S1

high · 7

  • high

    Tells Claude to install unpinned packages (deepspeed)

    references/other.md:110 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (packaging, setuptools, wheel, ninja)

    references/other.md:304 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (packaging, setuptools, wheel)

    references/other.md:323 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (awscli, pydantic)

    references/other.md:325 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@8a1a0ec)

    references/other.md:1609 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (packaging==23.2, setuptools==75.8.0, wheel, ninja)

    references/other.md:3072 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (packaging)

    references/other.md:3449 · skill_risk:S2

medium · 4

  • medium

    Tells Claude to install packages (torch==2.6.0)

    references/other.md:324 · skill_risk:S3

  • medium

    Tells Claude to install packages (librosa==0.11.0)

    references/other.md:449 · skill_risk:S3

  • medium

    Tells Claude to install packages (timm==1.0.17)

    references/other.md:457 · skill_risk:S3

  • medium

    Tells Claude to install packages (num2words==0.5.14)

    references/other.md:459 · skill_risk:S3

Versions

Version history

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

One version so far: v1 (1.0.0), seen 2026-11-03.

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.

Book a demo

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 research skills and plugins

See all