Waxell

skill

agentic-workflow-guide High risk

aktsmmaktsmm/agent-skillsupdated

Design, review, and debug agent workflows, and decide when a request should use a prompt, instruction, skill, agent, or hook before escalating to multi-agent design. Use for .agent.md / .instructions.md / .prompt.md / AGENTS.md work, workflow architecture, orchestration planning, scheduled automation model allocation, or when agent workflows may be overkill. Triggers on 'agent workflow', 'create agent', 'automation models', 'ワークフロー設計', 'orchestrator'.
aktsmm's own description, from the skill's files.
Stars
27
Version
v2
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 14 findings, highest severity high.

Highest severity
high
Findings
14
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: 14 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 (14)

high · 1

  • high

    Agent Snooping: Agent Config Directory Access

    references/hooks-guide.md:38 · skillspector:AS1

medium · 12

  • medium

    Prompt Injection: Whitespace Padding

    SKILL.md:34 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    references/agent-template.md:90 · skillspector:P9

  • medium

    Excessive Agency: Unrestricted Tool Access

    references/agent-template.md:226 · skillspector:EA1

  • medium

    Memory Poisoning: Context Window Stuffing

    references/context-engineering.md:228 · skillspector:MP2

  • medium

    Prompt Injection: Whitespace Padding

    references/context-engineering.md:252 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    references/context-engineering.md:283 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    references/customization-decision.md:7 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    references/customization-decision.md:51 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    references/customization-decision.md:53 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    references/design-principles.md:126 · skillspector:P9

  • medium

    Prompt Injection: Whitespace Padding

    references/external-resources.md:9 · skillspector:P9

  • medium

    Excessive Agency: Autonomous Decision Making

    references/review-checklist.md:74 · skillspector:EA2

low · 1

  • low

    Excessive Agency: Scope Creep

    LICENSE.txt:98 · skillspector:EA3

Versions

Version history

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

  1. v22026-11-169 changed High riskgot riskier
  2. v12026-11-03 No issues

Files

Files

29 files, 234 KB in total. Names only; open them on GitHub.

  • LICENSE.txt
  • SKILL.md
  • references/agent-evaluation.md
  • references/agent-guide.md
  • references/agent-template.md
  • references/builtin-customization-patterns.md
  • references/context-engineering.md
  • references/copilot-cloud-agent-ci.md
  • references/customization-decision.md
  • references/deep-agent-patterns.md
  • references/design-principles.md
  • references/external-resources.md
  • references/handoffs-guide.md
  • references/hooks-guide.md
  • references/prompt-template.md
  • references/review-checklist.md
  • references/scheduled-runtime-bindings.md
  • references/splitting-criteria.md
  • references/vscode-agent-placement.md
  • references/workflow-patterns/0-plan-first.md
  • references/workflow-patterns/1-prompt-chaining.md
  • references/workflow-patterns/2-routing.md
  • references/workflow-patterns/3-parallelization.md
  • references/workflow-patterns/4-orchestrator-workers.md
  • references/workflow-patterns/5-evaluator-optimizer.md
  • references/workflow-patterns/6-connected-agents.md
  • references/workflow-patterns/combining-patterns.md
  • references/workflow-patterns/ir-architecture.md
  • references/workflow-patterns/overview.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