Waxell

skill

skill-creator-plus High risk

aktsmmaktsmm/agent-skillsupdated

Create or review a reusable skill (SKILL.md) that packages a workflow, and decide whether the request should be a skill instead of a prompt, instruction, agent, or hook. Use when creating a new skill, extracting a workflow from a conversation, updating an existing skill, reviewing SKILL.md quality, or fixing weak skill triggering. Triggers on "create skill", "/create-skill", "new skill", "review skill", "fix skill trigger", "SKILL.md", "スキル作成".
aktsmm's own description, from the skill's files.
Stars
27
Version
v2
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 15 findings, highest severity high.

Highest severity
high
Findings
15
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: 15 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 (15)

high · 2

  • high

    Rogue Agent: Self-Modification

    references/creation-process.md:11 · skillspector:RA1

  • high

    Rogue Agent: Self-Modification

    references/creation-process.md:106 · skillspector:RA1

medium · 12

  • medium

    Without declared permissions the skill's intent is opaque and cannot be validated.

    SKILL.md:1 · skillspector:LP3

  • medium

    Prompt Injection: Whitespace Padding

    SKILL.md:19 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    SKILL.md:77 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    SKILL.md:79 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    SKILL.md:80 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    SKILL.md:83 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    SKILL.md:81 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    SKILL.md:82 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    SKILL.md:84 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    SKILL.md:85 · skillspector:P9

  • medium

    System Prompt Leakage: Indirect Prompt Extraction

    references/customization-primitives.md:39 · skillspector:P7

  • medium

    Rogue Agent: Session Persistence

    references/skill-review-checklist.md:142 · skillspector:RA2

low · 1

  • low

    Supply Chain: Unverifiable Dependency: PyYAML has 8 known advisory(ies) (CVE-2019-20477 (Deserialization of Untrusted Da

    scripts/requirements.txt:1 · skillspector:SC4

Versions

Version history

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

  1. v22026-11-162 changed High riskgot riskier
  2. v12026-11-03 No issues

Files

Files

25 files, 106 KB in total. Names only; open them on GitHub.

  • LICENSE.txt
  • PROVENANCE.md
  • SKILL.md
  • references/common-pitfalls.md
  • references/creation-process.md
  • references/customization-primitives.md
  • references/license-templates/apache-2.0.txt
  • references/license-templates/cc-by-nc-sa-4.0.txt
  • references/license-templates/mit.txt
  • references/output-patterns.md
  • references/skill-bloat-review.md
  • references/skill-review-checklist.md
  • references/skill-structure-gallery.md
  • references/skill-structure.md
  • references/target-license-profiles.json
  • references/validation-lanes.md
  • references/workflows.md
  • scripts/init_skill.py
  • scripts/license_metadata.py
  • scripts/package_skill.py
  • scripts/quick_validate.py
  • scripts/requirements.txt
  • scripts/test_init_skill.py
  • scripts/test_package_skill.py
  • scripts/test_quick_validate.py

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