SKILLEMALL.ai
GitHub ↗ RU Sign in

CC openclaw-agent-reputation

On-chain credit scoring and soulbound identity for autonomous agents

ClawHub Hermes author: Justin Liu v1.0.0 MIT-0 2 files body ≈ 3 539 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

ProcedureAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
C
72/100
safety, quality, tests
Safety 60%
81
Quality 40%
59
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
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. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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 · 7

✓ No critical or high findings

Medium and low: 7
  • medium Risky intent intent-wallet-secrets skill-card.md:36
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    **Other Properties Related to Output:** [Requires a wallet private key for transaction signing; on-chain writes can spend gas and create permanent public records.] <br>
  • medium Risky intent intent-wallet-secrets SKILL.md:623
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - `PRIVATE_KEY` (required): Ethereum wallet private key (for signing blockchain transactions)
  • medium Risky intent intent-wallet-secrets SKILL.md:625
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - Recommend using testnet wallet private key, not mainnet wallets with real assets
  • low Secrets in code secret-high-entropy-token SKILL.md:115
    High-entropy token-like string (may be an id, hash or a credential)
    帮我为我的 GPT-4 Agent 创建一个链上身份，地址是 0x74…bEb
  • low Secrets in code secret-high-entropy-token SKILL.md:124
    High-entropy token-like string (may be an id, hash or a credential)
    - agent_address: 0x74…bEb
  • low Secrets in code secret-high-entropy-token SKILL.md:444
    High-entropy token-like string (may be an id, hash or a credential)
    Help me create an on-chain identity for my GPT-4 Agent at address 0x74…bEb
  • low Secrets in code secret-high-entropy-token SKILL.md:453
    High-entropy token-like string (may be an id, hash or a credential)
    - agent_address: 0x74…bEb

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

Against the Agent Skills spec

  • warning description-long-hermes description is 68 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill
  • note frontmatter-key unknown frontmatter key "display_name"
  • note frontmatter-key unknown frontmatter key "subcategory"
  • note frontmatter-key unknown frontmatter key "repository"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "documentation"

Process rating: all ten parameters 58/100

  • 0Result and completion. Does not say what the result is
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 9 mutating operations with no state check
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Tools and files. No external tools needed
  • 100Steps. 172 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3539 tokens

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)
  • +3Description length 68: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -234 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +4Structure: 55 headings
  • +3Step-by-step instructions: 172 items
  • +4Has examples (24 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.

External checks

ClawHub: suspicious
This blockchain reputation skill appears legitimate, but it can spend wallet gas and create permanent public reputation records without clearly requiring explicit confirmation first.
LLM: suspicious (high) · VirusTotal: · 29 May 2026