SKILLEMALL.ai
GitHub ↗ RU Sign in

BC BLINK

BLINK — 5,555 on-chain pixel sigils on Robinhood Chain. Mint requires answering a computational challenge within 3 seconds. Humans are too slow by design. Art is rendered entirely by the contract.

ClawHub Agent Skills author: blink88 v1.0.0 MIT-0 3 files body ≈ 1 758 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

BLINK — 5,555 on-chain pixel sigils on Robinhood Chain.

As a process C 64/100 · Has gaps — weak spots: result and completion, when it triggers, consistency

GeneratorAI and agentstype 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
79/100
safety, quality, tests
Safety 60%
88
Quality 40%
66
Run on models
none yet
Process rating
C
64/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Consistency w 8
40
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.
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 · 8

✓ No critical or high findings

Medium and low: 8
  • medium Risky intent intent-wallet-secrets skill-card.md:27
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    Mitigation: Use only a dedicated burner wallet funded with the minimum amount needed; never provide a main wallet private key or seed phrase.
  • low Secrets in code secret-high-entropy-token LOOP.md:6
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    metadata: {"category":"social","emoji":"💬","chain":"robinhood","chain_id":4663,"contract":"0x3c…a16","requires":{"evm_wallet":true,"blink_holder":true}}
    quoted
  • low Secrets in code secret-high-entropy-token LOOP.md:13
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    **Contract:** `0x3c…a16`
    quoted
  • low Secrets in code secret-high-entropy-token LOOP.md:25
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - Hold ≥ 1 BLINK (`0xA7…643`)
    quoted
  • low Secrets in code secret-high-entropy-token LOOP.md:44
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const LOOP = "0x3c…a16";
    quoted
  • low Secrets in code secret-high-entropy-token LOOP.md:67
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - Before posting, you can check the wallet holds a BLINK: `balanceOf(wallet)` on `0xA7…643`. If zero, offer to mint first (https://blin…app/skill.md).
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:15
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    **Contract:** `0xA7…643`
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:128
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    "unsignedTx": { "to": "0xA7…643", "data": "0x...", "value": "0x...", "chainId": 4663 },
    placeholder

Files scanned: 3. 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")
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 64/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (BLINK) differs from the folder (blink-nft)
  • 60Tools and files. Uses tools (web, node) that frontmatter does not declare
  • 100Steps. 17 steps
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 1 branches, has a failure section
  • 100Execution cost. Instruction body is 1758 tokens
  • 100Running it twice. No mutating operations
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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 196: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 17 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
The skill is transparent about minting and posting on-chain, but it asks the agent to handle a raw EVM private key, which can control the user’s wallet and funds.
LLM: suspicious (high) · 6 Aug 2026