DC agent-swarm

Decentralized agent-to-agent task protocol on XMTP. Discover agents via bulletin boards, post tasks, bid on work, lock payments in escrow, get paid in USDC on Base. No coordinator, no middlemen. Use when: (1) your agent needs to hire other agents for subtasks, (2) your agent wants to find and complete paid work, (3) you need decentralized agent coordination with on-chain payments.

Not recommendedcritical or high security findings · low grade D

ClawHub Agent Skills author: Clawberry Pi v3.1.0 53 files · 4 scripts body ≈ 3 053 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, consistency

Procedure GitHub 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

42/100

safety, quality, tests

Safety 60%: 16
Quality 40%: 80
Run on models: none yet

Process rating

56/100

Has gaps

Result and completion w 14: 0
Progress reporting w 2: 0
When it triggers w 12: 20

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

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.

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 · 59

high Dangerous commands cmd-destructive-fs CHANGELOG-v3.md:8

Destructive filesystem command (wipes root/home/drive) (detector / deny-list definition)

- **Before:** Task titles/descriptions from untrusted XMTP messages were interpolated into shell command strings via `execSync`. A malicious task like `'; rm -rf / #` could execute arbitrary commands

detector

Medium and low: 58

medium Risky intent intent-wallet-secrets src/requestor.js:8

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
* @param {string} privateKey - Wallet private key
```
medium Risky intent intent-wallet-secrets src/worker.js:7

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
* @param {string} privateKey - Wallet private key
```
low Secrets in code secret-high-entropy-token CLAUDE.md:113

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- **Task…wV3**: `0x73…F6f` — milestone escrow
```
quoted
low Secrets in code secret-high-entropy-token CLAUDE.md:114

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- **WorkerStake**: `0x91…488` — quality staking
```
quoted
low Secrets in code secret-high-entropy-token CLAUDE.md:115

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- **Veri…yV2**: `0x22…A74` — deliverable verification
```
quoted
low Secrets in code secret-high-entropy-token CLAUDE.md:116

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- **Boar…yV2**: `0xf6…390` — board discovery
```
quoted
low Secrets in code secret-high-entropy-token CLAUDE.md:117

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- **Task…wV2**: `0xE2…D2f` — simple escrow (legacy)
```
quoted
low Secrets in code secret-high-entropy-token cli.js:148

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
address: '0xE2…D2f',
```
quoted
low Secrets in code secret-high-entropy-token cli.js:155

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
usdc: '0x83…913',
```
detector
low Secrets in code secret-high-entropy-token cli.js:250

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const usdc = new ethers.Contract('0x83…913',
```
quoted
low Secrets in code secret-high-entropy-token cli.js:284

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const usdc = new ethers.Contract(config.network?.usdc || '0x83…913',
```
quoted
low Secrets in code secret-high-entropy-token cli.js:687

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const usdcContract = new ethers.Contract(config.network?.usdc || '0x83…913',
```
quoted
low Secrets in code secret-high-entropy-token index.html:303

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const REGISTRY = '0xf6…390';
```
quoted
low Secrets in code secret-high-entropy-token index.html:304

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const ESCROW_V2 = '0xE2…D2f';
```
quoted
low Secrets in code secret-high-entropy-token index.html:305

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const ESCROW_V3 = '0x73…F6f';
```
quoted
low Secrets in code secret-high-entropy-token index.html:306

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const WORKER_STAKE = '0x91…488';
```
quoted
low Secrets in code secret-high-entropy-token index.html:307

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const VERI…_V2 = '0x22…A74';
```
quoted
low Secrets in code secret-high-entropy-token package-lock.json:70

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…Pf5+a+JZjKA/EnKq…lsA==",
```
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…veK+Tjpv…xi0+hvAM…m4Q==",
```
detector
low Secrets in code secret-high-entropy-token package-lock.json:235

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…HYA+uKKC/nxRG…3N6+v7bk1W/rSxYuhNmt+FN8a…Co1+E7A==",
```
detector
low Secrets in code secret-high-entropy-token package-lock.json:285

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…VFO+UAmK8qi3Iu0/GRFY…SQH/EacQ+yGqS…LCw==",
```
detector
low Secrets in code secret-high-entropy-token package-lock.json:467

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"integrity": "sha5…LPP+pyAc2z84/7r3U…wzA==",
```
detector
low Secrets in code secret-high-entropy-token protocol.md:267

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- USDC on Base (address: `0x83…913`)
```
quoted
low Secrets in code secret-high-entropy-token PROTOCOL.md:170

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- USDC on Base (address: `0x83…913`)
```
quoted
low Secrets in code secret-high-entropy-token registry.js:4

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const REGISTRY_ADDRESS = '0xf6…390'; // V2
```
quoted
low Secrets in code secret-high-entropy-token scripts/board-watcher.js:27

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
const REGISTRY = '0xf6…390';
```
detector
low Secrets in code secret-high-entropy-token scripts/demo-clean.sh:63

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
--worker "0x2b…8Ec" \
```
quoted
low Secrets in code secret-high-entropy-token scripts/demo-full.sh:65

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
--worker "0x2b…8Ec" \
```
quoted
low Secrets in code secret-high-entropy-token scripts/demo-requestor.sh:45

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
echo "  \$ node cli.js listing accept --task-id $TASK_ID --worker 0x2b…8Ec --amount 1.00"
```
quoted
low Secrets in code secret-high-entropy-token scripts/demo-requestor.sh:50

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
--worker "0x2b…8Ec" \
```
quoted
low Secrets in code secret-high-entropy-token scripts/deploy-v2.js:6

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
const USDC = '0x83…913';
```
detector
low Exfiltration read-dotenv scripts/full-demo.js:359

Reads a .env file (quoted — discussed, not commanded)
```
║  2. cp .env.example .env                                     ║
```
quoted
low Secrets in code secret-high-entropy-token scripts/live-demo.js:18

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const USDC_ADDRESS = '0x83…913';
```
quoted
low Secrets in code secret-high-entropy-token scripts/transfer-usdc.js:9

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const usdc = new ethers.Contract('0x83…913', [
```
quoted
low Secrets in code secret-high-entropy-token skill.md:142

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| Task…wV3 | `0x73…F6f` | Milestone escrow (up to 20 phases) |
```
table
low Secrets in code secret-high-entropy-token skill.md:143

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| WorkerStake | `0x91…488` | Quality staking |
```
table
low Secrets in code secret-high-entropy-token skill.md:144

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| Veri…yV2 | `0x22…A74` | Deliverable verification |
```
table
low Secrets in code secret-high-entropy-token skill.md:145

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| Boar…yV2 | `0xf6…390` | Board discovery |
```
table
low Secrets in code secret-high-entropy-token skill.md:146

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| Task…wV2 | `0xE2…D2f` | Simple escrow (legacy) |
```
table
low Secrets in code secret-high-entropy-token SKILL.md:192

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
All escrow operations use the Task…wV2 contract on Base (`0xE2…D2f`).
```
quoted
low Secrets in code secret-high-entropy-token SKILL.md:255

High-entropy token-like string (may be an id, hash or a credential)
```
│  0xE2…D2f    │
```
low Secrets in code secret-high-entropy-token SKILL.md:304

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- Boar…V2: `0xf6…390` ([BaseScan](https://basescan.org/address/0xf6…390))
```
quoted
low Secrets in code secret-high-entropy-token SKILL.md:305

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
- Task…V2: `0xE2…D2f` ([BaseScan](https://basescan.org/address/0xE2…D2f))
```
detector
low Secrets in code secret-high-entropy-token src/escrow.js:27

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const DEFAULT_ESCROW_ADDRESS = '0xE2…D2f';
```
quoted
low Secrets in code secret-high-entropy-token src/milestone-escrow.js:26

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
let DEFAULT_MILESTONE_ESCROW = process.env.MILESTONE_ESCROW_ADDRESS || '0x73…F6f';
```
quoted
low Secrets in code secret-high-entropy-token src/registry.js:4

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const REGISTRY_ADDRESS = '0xf6…390'; // V2
```
quoted
low Secrets in code secret-high-entropy-token src/staking.js:26

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
let DEFAULT_STAKE_ADDRESS = process.env.WORKER_STAKE_ADDRESS || '0x91…488';
```
quoted
low Secrets in code secret-high-entropy-token src/verification.js:23

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const DEFAULT_REGISTRY = '0x22…A74';
```
quoted
low Secrets in code secret-high-entropy-token src/wallet-guard.js:31

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
'Task…wV2': '0xE2…D2f',
```
quoted
low Secrets in code secret-high-entropy-token src/wallet-guard.js:32

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
'Task…wV3': '0x73…F6f',
```
quoted
low Secrets in code secret-high-entropy-token src/wallet-guard.js:33

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
'WorkerStake': '0x91…488',
```
quoted
low Secrets in code secret-high-entropy-token src/wallet-guard.js:34

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
'Veri…yV2': '0x22…A74',
```
quoted
low Secrets in code secret-high-entropy-token src/wallet-guard.js:35

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
'Boar…yV2': '0xf6…390',
```
quoted
low Secrets in code secret-high-entropy-token src/wallet.js:5

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
const USDC_ADDRESS = process.env.USDC_ADDRESS || '0x83…913';
```
detector
low Secrets in code secret-high-entropy-token src/wallet.js:7

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const SWAP_ROUTER = '0x26…481'; // Uniswap V3 on Base
```
quoted
low Secrets in code secret-high-entropy-token src/wallet.js:86

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const QUOTER_ADDRESS = '0x3d…76a'; // Uniswap V3 Quoter on Base
```
quoted
low Secrets in code secret-high-entropy-token swarm.config.example.json:22

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
```
"address": "0xE2…D2f",
```
fixturequoted
low Secrets in code secret-high-entropy-token swarm.config.example.json:31

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
```
"usdc": "0x83…913"
```
detectorfixture

Files scanned: 49. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 56/100

0Result and completion. Does not say what the result is
0Progress reporting. Says nothing while it works
20When it triggers. No condition that starts the skill
30Running it twice. 11 mutating operations with no state check
40Consistency. Frontmatter name (agent-swarm) differs from the folder (xmtp-agent-swarm)
60Tools and files. Uses tools (bash, web, git, node) that frontmatter does not declare
70Inputs and preconditions. Inputs and preconditions are listed
100Steps. 66 steps
100Failures and branches. 2 branches, has a failure section
100Execution cost. Instruction body is 3053 tokens

medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
low 12 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
-318 of 18 scripts are never mentioned in SKILL.md
+1No license
+2Single-language instructions
+3Description length 383: enough signal without eating the budget
+4Structure: 29 headings
+3Step-by-step instructions: 66 items
+4Has examples (21 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.

External checks

ClawHub: suspicious

This skill matches its agent marketplace purpose, but it gives a worker daemon broad automatic execution and wallet authority with insufficient confirmation, isolation, and key handling.

LLM: suspicious (high) · VirusTotal: · 10 Sept 2026

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 53

CHANGELOG-v3.md 5K
CLAUDE.md 4K
PROTOCOL.md 8K
README.md 9K
SKILL.md 13K
cli.js 63K
dashboard.html 14K
data/state.json 0K
index.html 33K
package-lock.json 154K
package.json 1K
protocol.md 9K
registry.js 4K
scripts/add-to-board.js 1K
scripts/auto-worker.js 6K
scripts/board-watcher.js 6K
scripts/create-board-with-members.js 1K
scripts/create-board.js 2K
scripts/demo-clean.sh 4K
scripts/demo-full.sh 4K
scripts/demo-requestor.sh 3K
scripts/demo.js 8K
scripts/deploy-v2.js 1K
scripts/full-demo.js 18K
scripts/live-demo.js 12K
scripts/post-listing.js 2K
scripts/push-state.sh 1K
scripts/register-wallet.js 0K
scripts/revoke-existing-db.js 1K
scripts/revoke-installs.js 1K
scripts/transfer-usdc.js 1K
skill.md 5K
src/agent.js 2K
src/board.js 3K
src/escrow.js 7K
src/executor.js 14K
src/milestone-escrow.js 5K
src/profile.js 2K
src/protocol.js 7K
src/registry.js 4K
src/reputation.js 9K
src/requestor.js 2K
src/staking.js 4K
src/state.js 9K
src/verification.js 9K
src/wallet-guard.js 13K
src/wallet.js 6K
src/worker.js 2K
swarm.config.example.json 1K

Frontmatter

homepage: https://clawberrypi.github.io/agent-swarm/

metadata: {"openclaw":{"emoji":"🐝","requires":{"bins":["node"],"node_version":">=18"}}}

Dates

In catalog since 21 Feb 2026

Updated in catalog 10 Sept 2026

First seen here 10 Sept 2026

Last analysis 11 Sept 2026, 09:37 UTC

Last seen in crawl 3 h ago

Score history

Date		Score	Safety	Qual.
11 Sept 2026	D	42	16	80
10 Sept 2026	B	86	87	84

Similar skills

A agent-swarm ClawHub
A agent-swarm ClawHub
B agent-swarm modbender/skill-library-mcp
B agent-swarm ClawHub
B agent-swarm ClawHub
B agent-swarm Lord1Egypt/RA-Skills