SKILLEMALL.ai
GitHub ↗ RU Sign in

BC credex-protocol

Access unsecured credit lines for AI agents on the Arc Network using the Credex Protocol. Use for borrowing USDC against reputation, repaying debt to grow credit limits, providing liquidity as an LP, or managing cross-chain USDC via Circle Bridge. Triggers on "borrow from credex", "repay debt", "deposit to pool", "check credit status", "provide liquidity", or any credit/lending task on Arc.

modbender/skill-library-mcp Agent Skills author: modbender MIT 7 files body ≈ 2 204 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Access unsecured credit lines for AI agents on the Arc Network using the Credex Protocol.

As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, progress reporting

ProcedureAI 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
87/100
safety, quality, tests
Safety 60%
81
Quality 40%
97
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Failures and branches w 10
50
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

    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 · 11

    ✓ No critical or high findings

    Medium and low: 11
    • medium Risky intent intent-wallet-secrets scripts/client.ts:19
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      *   WALLET_PRIVATE_KEY  (required) Your wallet private key
    • medium Risky intent intent-wallet-secrets scripts/lp.ts:20
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      *   WALLET_PRIVATE_KEY  (required) Your wallet private key
    • low Secrets in code secret-high-entropy-token package-lock.json:57
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…jyV+xktW…ZFZ+Q==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:128
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…m48+9Ovm…EqH/ti/7ASj…sop+LQ==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:146
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…kJw+JUEz…Ry8+JzNy…KLw==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:171
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…7pY+zoMV…h0x/Ptw8…8dg==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:188
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…b00+Gxjx…zRc/oZwU…hzA==",
      detector
    • low Secrets in code secret-high-entropy-token references/contracts.md:12
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      USDC_BASE_SEPOLIA: "0x03…F7e",
      quoted
    • low Secrets in code secret-high-entropy-token scripts/client.ts:43
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      USDC_BASE: getAddress("0x03…F7e"),
      quoted
    • low Secrets in code secret-high-entropy-token scripts/lp.ts:43
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      USDC_BASE: getAddress("0x03…F7e"),
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:54
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | `USDC` (Base Sepolia) | `0x03…F7e` |
      table

    Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 63/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (node) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 85Steps. 15 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2204 tokens
    • 100Running it twice. No mutating operations

    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

    • +4Description does not say when NOT to use the skill (false activations)
    • -2localhost URLs: will not work for another user
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 5 example trigger phrases
    • +3Description length 393: enough signal without eating the budget
    • +4Structure: 27 headings
    • +3Step-by-step instructions: 15 items
    • +3Output format is stated explicitly
    • +4Has examples (24 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.