SKILLEMALL.ai
GitHub ↗ RU Sign in

CF verdikta-bounties-onboarding

Onboard an OpenClaw/AI agent to Verdikta Bounties. Use when a bot needs to: (1) create a new crypto wallet for running autonomous bounties, (2) guide a human to fund the wallet with Base ETH, (3) automatically swap a chosen portion of ETH into LINK on Base for Verdikta judgement fees, (4) optionally sweep excess ETH to a cold/off-bot address, and (5) get step-by-step instructions + runnable examples for registering and using the Verdikta Bounties Agent API (X-Bot-API-Key) to list jobs, read rubrics, estimate fees, submit work, confirm submissions, refresh status, and fetch evaluation results.

modbender/skill-library-mcp Agent Skills author: modbender MIT 23 files body ≈ 7 012 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Onboard an OpenClaw/AI agent to Verdikta Bounties.

As a process F 44/100 · Will not run — References files that are not bundled: scripts/.env

ProcedureGitHubAI and agentsSoftware developmentWriting and documentstype 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
69/100
safety, quality, tests
Safety 60%
69
Quality 40%
68
Run on models
none yet
Process rating
F
44/100
Will not run
References files that are not bundled: scripts/.env
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
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 · 15

✓ No critical or high findings

Medium and low: 15
  • medium Risky intent intent-wallet-secrets README.md:54
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    2. Create a new wallet, or import an existing private key / keystore file
  • medium Risky intent intent-wallet-secrets references/security.md:9
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - Store the keystore file with `chmod 600` and outside web roots.
  • medium Exfiltration net-redirectable-api-key scripts/onboard.js:233
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key scripts/swap_eth_to_link_0x.js:22
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • low Secrets in code secret-high-entropy-token scripts/_lib.js:9
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    base: '0x88…196',
    quoted
  • low Secrets in code secret-high-entropy-token scripts/_lib.js:10
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'base-sepolia': '0xE4…410'
    quoted
  • low Secrets in code secret-high-entropy-token scripts/_lib.js:23
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'base': process.env.BOUNTY_ESCROW_ADDRESS_BASE || '0x0a…746',
    quoted
  • low Secrets in code secret-high-entropy-token scripts/_lib.js:24
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'base-sepolia': process.env.BOUNTY_ESCROW_ADDRESS_BASE_SEPOLIA || '0x05…780',
    quoted
  • low Exfiltration net-credential-use scripts/claim_bounty.js:201
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    console.log(`  curl -H "X-Bot-API-Key: ${safeKey}" ${baseUrl}/api/jobs/${jobId}/submissions/${submissionId}/evaluation`);
    quoted
  • low Secrets in code secret-high-entropy-token scripts/create_bounty_min.js:22
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    const evaluationCid = arg('cid', 'QmRL…rtX');
    detector
  • low Risky intent intent-wallet-secrets scripts/onboard.js:110
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    console.log('  3) Import an existing keystore file');
    quoted
  • low Risky intent intent-wallet-secrets scripts/onboard.js:126
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    if (!(await fileExists(srcAbs))) throw new Error(`Keystore file not found: ${srcAbs}`);
    quoted
  • low Exfiltration net-credential-use scripts/submit_to_bounty.js:415
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    console.log(`  curl -X POST -H "X-Bot-API-Key: ${safeKey}" ${baseUrl}/api/jobs/${jobId}/submissions/${submissionId}/refresh`);
    quoted
  • low Exfiltration net-credential-use scripts/submit_to_bounty.js:416
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    console.log(`  curl -H "X-Bot-API-Key: ${safeKey}" ${baseUrl}/api/jobs/${jobId}/submissions/${submissionId}/evaluation`);
    quoted
  • low Risky intent intent-wallet-secrets SKILL.md:121
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    - Run `node scripts/onboard.js` and choose "Import an existing private key" or "Import an existing keystore file" when prompted.
    quoted

Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7012 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/.env

Process rating: all ten parameters 44/100

Will not run. References files that are not bundled: scripts/.env
  • 0Tools and files. 1 referenced file(s) missing: scripts/.env
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 35 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 70Execution cost. Instruction body is 7012 tokens
  • 85Steps. 106 steps, 1 vague phrases
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 17 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
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • -32 of 16 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 599: enough signal without eating the budget
  • +4Structure: 37 headings
  • +3Step-by-step instructions: 106 items
  • +4Has examples (26 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.