SKILLEMALL.ai
GitHub ↗ RU Sign in

BC greenhelix-agent-compliance-toolkit

EU AI Act Compliance for Autonomous Agents. Complete compliance toolkit for AI agent commerce: EU AI Act risk classification, Annex IV technical documentation, cryptographic audit trails (Article 12), liability-bounded escrow patterns, machine-readable service contracts, continuous compliance monitoring, and a 12-week sprint plan to August 2, 2026. Includes working Python code, contract templates, and checklists.

ClawHub Agent Skills author: mirni v1.3.1 MIT-0 2 files body ≈ 30 578 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, execution cost

AnalyzerSecurityAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
83/100
safety, quality, tests
Safety 60%
99
Quality 40%
60
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Execution cost w 6
10
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 1

✓ No critical or high findings

Medium and low: 1
  • low Risky intent intent-offensive-security SKILL.md:1945
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Run penetration testing against compliance infrastructure.

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 30578 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "type"
  • note frontmatter-key unknown frontmatter key "price_usd"
  • note frontmatter-key unknown frontmatter key "content_type"
  • note frontmatter-key unknown frontmatter key "executable"
  • note frontmatter-key unknown frontmatter key "install"
  • note frontmatter-key unknown frontmatter key "credentials"

Process rating: all ten parameters 61/100

  • 0Result and completion. Does not say what the result is
  • 10Execution cost. Instruction body is 30578 tokens: crowds the task out of the window
  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 108 steps
  • 100Failures and branches. 19 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 12 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +3Description length 416: enough signal without eating the budget
  • +4Structure: 61 headings
  • +3Step-by-step instructions: 108 items
  • +4Has examples (17 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.

External checks

ClawHub: suspicious
The skill is a non-installing compliance guide, but it includes runnable production-capable examples that can change GreenHelix accounts, escrows, disputes, webhooks, and monitoring state with unclear sandbox versus production boundaries.
LLM: suspicious (high) · VirusTotal: · 29 May 2026