BD Agent Wallet SDK Skill

Non-custodial wallet SDK for autonomous AI agents. Handles x402 payments, CCTP V2 cross-chain bridge transfers, ERC-8004 agent identity, and Uniswap V3 token swaps — all without holding user keys.

modbender/skill-library-mcp Agent Skills author: modbender MIT 20 files body ≈ 769 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Non-custodial wallet SDK for autonomous AI agents.

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

Integration AI 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

79/100

safety, quality, tests

Safety 60%: 79
Quality 40%: 79
Run on models: none yet

Process rating

46/100

Unfinished process

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

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 · 21

✓ No critical or high findings

Medium and low: 21

low Secrets in code secret-high-entropy-token agent-wallet-sdk/examples/micropayment-agent.ts:23

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
const USDC = '0x83…913' as Address;
```
fixturequoted
low Secrets in code secret-high-entropy-token agent-wallet-sdk/examples/trading-agent.ts:26

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
const USDC = '0x83…913' as Address; // USDC on Base
```
fixturequoted
low Secrets in code secret-high-entropy-token agent-wallet-sdk/examples/trading-agent.ts:27

High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
```
const POLYMARKET_CTF_EXCHANGE = '0x4b…82E' as Address; // example
```
placeholder
low Secrets in code secret-high-entropy-token agent-wallet-sdk/test/sdk.test.ts:50

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
const OPERATOR: Address = '0xBB…BBB';
```
fixturequoted
low Secrets in code secret-high-entropy-token agent-wallet-sdk/test/sdk.test.ts:51

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
const TOKEN: Address = '0xCC…CCC';
```
fixturequoted
low Secrets in code secret-high-entropy-token agent-wallet-sdk/test/sdk.test.ts:52

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
const FACTORY: Address = '0xDD…DDD';
```
fixturequoted
low Secrets in code secret-high-entropy-token CHANGELOG.md:29

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- **Base Mainnet** — Agen…V2: `0x70…8A1`
```
quoted
low Secrets in code secret-high-entropy-token CHANGELOG.md:30

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- **Base Mainnet** — AgentNexusEscrow: `0x37…2fC`
```
quoted
low Secrets in code secret-high-entropy-token CHANGELOG.md:31

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- **Base Mainnet** — AgentNexusEntitlements: `0x3c…b33`
```
quoted
low Secrets in code secret-high-entropy-token DEPLOYMENTS.md:9

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| **AgentNexusEscrow**       | `0x37…2fC` | [BaseScan](https://basescan.org/address/0x37…2fC) |
```
table
low Secrets in code secret-high-entropy-token DEPLOYMENTS.md:10

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
```
| **AgentNexusEntitlements** | `0x3c…b33` | [BaseScan](https://basescan.org/address/0x3c…b33) |
```
detectortable
low Secrets in code secret-high-entropy-token DEPLOYMENTS.md:20

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| AgentNexusEscrow       | `0xCb…1b5` | [BaseScan](https://sepolia.basescan.org/address/0xCb…1b5) |
```
table
low Secrets in code secret-high-entropy-token DEPLOYMENTS.md:21

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
```
| AgentNexusEntitlements | `0x53…1c9` | [BaseScan](https://sepolia.basescan.org/address/0x53…1c9) |
```
detectortable
low Secrets in code secret-high-entropy-token README.md:46

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| **Base Mainnet** | Agen…yV2 | [`0x70…8A1`](https://basescan.org/address/0x70…8A1) |
```
table
low Secrets in code secret-high-entropy-token README.md:47

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
```
| **Base Sepolia** | Agen…yV2 | [`0x33…3Be`](https://sepolia.basescan.org/address/0x33…3Be) |
```
detectortable
low Risky intent intent-offensive-security SECURITY.md:158

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
- No privilege escalation
```
low Dangerous commands cmd-privilege SECURITY.md:237

Privilege escalation / world-writable permissions (documentation of a security skill)
```
- Setuid/setgid attacks
```
security skill
low Dangerous commands cmd-privilege SECURITY.md:263

Privilege escalation / world-writable permissions (documentation of a security skill)
```
❌ **Privilege:** setuid, setgid, capset
```
security skill
low Risky intent intent-offensive-security SECURITY.md:372

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
#### ✅ Privilege Escalation
```
low Risky intent intent-offensive-security SECURITY.md:421

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
- Penetration testing (optional)
```
low Risky intent intent-offensive-security SECURITY.md:513

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
**Bug Bounty:** Coming soon
```

Files scanned: 20. 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)

Process rating: all ten parameters 46/100

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. 1 mutating operations with no state check
40Consistency. Frontmatter name (Agent Wallet SDK Skill) differs from the folder (agentwallet-sdk)
100Tools and files. No external tools needed
100Steps. 13 steps
100Execution cost. Instruction body is 769 tokens

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: 14 headings
+3Step-by-step instructions: 13 items
+4Has examples (8 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 20

ARCHITECTURE.md 2K
AUDIT_REPORT.md 14K
AUDIT_REPORT_V2.md 2K
CHANGELOG.md 2K
DEPLOYMENTS.md 2K
KNOWN_ISSUES.md 3K
README.md 5K
SECURITY.md 12K
SKILL.md 3K
VALIDATION_REPORT.md 8K
agent-wallet-sdk/examples/micropayment-agent.ts 4K
agent-wallet-sdk/examples/trading-agent.ts 3K
agent-wallet-sdk/package.json 1K
agent-wallet-sdk/src/abi.ts 7K
agent-wallet-sdk/src/index.ts 15K
agent-wallet-sdk/src/types.ts 3K
agent-wallet-sdk/test/sdk.test.ts 17K
agent-wallet-sdk/tsconfig.json 0K
skill.json 1K
smart-contracts/foundry.toml 2K

When to use

Use this skill when an AI agent needs to: - Create or manage a non-custodial wallet (ERC-4337 smart account) - Make x402 HTTP payments to APIs - Bridge tokens cross-chain via CCTP V2 (Circle) - Swap tokens via Uniswap V3 - Register or verify agent identity via ERC-8004 - Sign transactions autonomously without custodial risk

Dates

In catalog since —

Updated in catalog 16 Jun 2026

First seen here 7 Sept 2026

Last analysis 11 Sept 2026, 17:26 UTC

Last seen in crawl 35 h ago

Score history

Date		Score	Safety	Qual.
10 Sept 2026	B	79	79	79
7 Sept 2026	B	78	79	76
7 Sept 2026	B	75	79	70