SKILLEMALL.ai
GitHub ↗ RU Sign in

DC a2a-shib-payments

Framework-agnostic agent-to-agent payment system with SHIB on Polygon. Provides trustless escrow, price negotiation, and reputation system. 9,416x cheaper than traditional escrow (~$0.003 gas).

Not recommendedcritical or high security findings · low grade D
modbender/skill-library-mcp Agent Skills author: modbender MIT 43 files · 2 scripts body ≈ 1 765 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Framework-agnostic agent-to-agent payment system with SHIB on Polygon.

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationGitHubAI and agentsSales and CRMtype 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
D
54/100
safety, quality, tests
Safety 60%
45
Quality 40%
68
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. 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 · 22

  • high Dangerous commands cmd-persistence DEPLOYMENT.md:401
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null; echo "0 * * * * cd $(pwd) && ./backup.sh") | crontab -
Medium and low: 21
  • medium Dangerous commands cmd-privilege deploy-local.sh:26
    Privilege escalation / world-writable permissions
    sudo cp shib-payment-agent.service /etc/systemd/system/
  • medium Dangerous commands cmd-privilege DEPLOYMENT.md:391
    Privilege escalation / world-writable permissions
    sudo cp shib-payment-agent.service /etc/systemd/system/
  • medium Dangerous commands cmd-privilege DEPLOYMENT.md:460
    Privilege escalation / world-writable permissions
    sudo cp shib-payment-agent.service /etc/systemd/system/
  • medium Risky intent intent-wallet-secrets SKILL.md:97
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - `WALLET_PRIVATE_KEY` - Your Polygon wallet private key
  • low Secrets in code secret-high-entropy-token a2a-agent-production.js:186
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    `🦪 SHIB Payment Agent (Production)\n\nCommands:\n- send <amount> SHIB to <address>\n- balance\n\n🔒 Security:\n- API key required (X-API-Key header)\n- Rate limit: 3 payments/min\n- Max payment: Chec
    quoted
  • low Secrets in code secret-high-entropy-token a2a-agent-v2.js:109
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    `🦪 SHIB Payment Agent\n\nCommands:\n- send <amount> SHIB to <address>\n- balance\n\nExample: send 100 SHIB to 0xDB…99A`
    quoted
  • low Secrets in code secret-high-entropy-token check_balance_temp.js:5
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const address = '0xDB…99A';
    quoted
  • low Exfiltration read-dotenv CONTRIBUTING.md:64
    Reads a .env file
    cp .env.example .env.local
  • low Secrets in code secret-high-entropy-token demo-requestor-agent.js:75
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    '0xDB…99A', // Coinbase Polygon wallet
    quoted
  • low Dangerous commands cmd-background-process deploy-local.sh:33
    Starts a background / autostarted process
    sudo systemctl enable shib-payment-agent
  • low Dangerous commands cmd-background-process DEPLOYMENT.md:110
    Starts a background / autostarted process
    sudo systemctl enable shib-payment-agent
  • low Exfiltration read-dotenv DEPLOYMENT.md:193
    Reads a .env file
    cp .env.example .env.local
  • low Dangerous commands cmd-background-process DEPLOYMENT.md:393
    Starts a background / autostarted process
    sudo systemctl enable shib-payment-agent
  • low Dangerous commands cmd-cron-mention DEPLOYMENT.md:401
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null; echo "0 * * * * cd $(pwd) && ./backup.sh") | crontab -
  • low Dangerous commands cmd-background-process DEPLOYMENT.md:461
    Starts a background / autostarted process
    sudo systemctl enable shib-payment-agent
  • low Exfiltration read-dotenv INTEGRATION-EXAMPLES.md:275
    Reads a .env file (test fixture / example file)
    cp .env.example .env.local
    fixture
  • low Secrets in code secret-high-entropy-token PRODUCTION-HARDENING.md:94
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "recipient": "0xDB…99A",
    quoted
  • low Exfiltration read-dotenv README.md:114
    Reads a .env file
    cp .env.example .env.local
  • low Exfiltration read-dotenv SKILL.md:92
    Reads a .env file
    cp .env.example .env.local
  • low Secrets in code secret-high-entropy-token SUCCESS.md:37
    High-entropy token-like string (may be an id, hash or a credential)
    - **From:** 0x26…7C5 (MetaMask)
  • low Secrets in code secret-high-entropy-token SUCCESS.md:38
    High-entropy token-like string (may be an id, hash or a credential)
    - **To:** 0xDB…99A (Coinbase)

Files scanned: 43. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 51/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 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. 16 mutating operations with no state check
  • 100Tools and files. No external tools needed
  • 100Steps. 80 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1765 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 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
  • -2localhost URLs: will not work for another user
  • -217 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 193: enough signal without eating the budget
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 80 items
  • +4Has examples (8 code blocks)

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