SKILLEMALL.ai
GitHub ↗ RU Sign in

CD Web3 & Blockchain Engineering

Complete methodology for evaluating, designing, building, securing, and operating blockchain-based systems. Covers smart contract development, DeFi protocol design, token economics, security auditi...

modbender/skill-library-mcp Agent Skills author: modbender MIT 2 files body ≈ 9 286 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Complete methodology for evaluating, designing, building, securing, and operating blockchain-based systems.

As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerInfrastructureSecuritytype 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
C
74/100
safety, quality, tests
Safety 60%
86
Quality 40%
57
Run on models
none yet
Process rating
D
45/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Risky intent medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

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 · 6

✓ No critical or high findings

Medium and low: 6
  • medium Risky intent intent-wallet-secrets SKILL.md:630
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    Seed Phrase (BIP-39)
  • medium Risky intent intent-wallet-secrets SKILL.md:670
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    1. **Seed phrase storage** — Metal plate (Cryptosteel/Billfodl), never digital
  • low Risky intent intent-offensive-security SKILL.md:420
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - [ ] Bug bounty program launched
  • low Risky intent intent-offensive-security SKILL.md:561
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - [ ] Bug bounty program live (Immunefi)
  • low Risky intent intent-offensive-security SKILL.md:898
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Security | 25% | 0: No audit, known vulns. 50: Basic testing. 100: Full audit, bug bounty, formal verification |
  • low Risky intent intent-offensive-security SKILL.md:945
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - $1M+ bug bounty on Immunefi

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

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 9286 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 45/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 12 mutating operations with no state check
  • 40Consistency. Frontmatter name (Web3 & Blockchain Engineering) differs from the folder (afrexai-web3-engineering)
  • 40Execution cost. Instruction body is 9286 tokens: crowds the task out of the window
  • 50Failures and branches. 0 branches, has a failure section
  • 85Steps. 119 steps, 2 vague phrases
  • 100Tools and files. No external tools needed
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 16 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
  • +1No license
  • +2Single-language instructions
  • +3Description length 200: enough signal without eating the budget
  • +4Structure: 59 headings
  • +3Step-by-step instructions: 119 items
  • +4Has examples (18 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.