Skills/ClawHub/xmtp-agent-swarm

xmtp-agent-swarm@3.1.0

CAUTION· static only

Publisher claims: "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." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher clawberrypi · publishing for 263 daysInstalls 1,943Last detonated 7d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-07 and scored it 58/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Access to sensitive file pathscli.js:78 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: config.xmtp?.env || 'production',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdashboard/skill.md:51 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesCreate a `.env` file with your agent's Ethereum private key:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/demo.js:10 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprocess.loadEnvFile('.env');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/full-demo.js:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprocess.loadEnvFile('.env');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/create-board.js:7 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprocess.loadEnvFile('.env');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/full-demo.js:359 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files║ 2. cp .env.example .env ║Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathscli.js:293 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconsole.log(`XMTP: ${config.xmtp?.env || 'production'}`);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/demo.js:9 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// Load .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/full-demo.js:360 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files║ 3. Add your private key to .env ║Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionscripts/full-demo.js:319 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('Requestor reputation:');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actioncli.js:263 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` (Only needed if you want to post tasks with escrow)`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagescripts/full-demo.js:358 · npx invocation of non-well-known package — may execute untrusted code║ 1. npx clawhub install xmtp-agent-swarm ║Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsscripts/post-listing.js:9 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprocess.loadEnvFile('.env');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionscripts/full-demo.js:320 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(formatReputation(reqRep));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actioncli.js:259 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`\n⚠️ No ETH for gas. Send Base ETH to: ${wallet.address}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actioncli.js:268 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(' Post a listing: node cli.js listing post --title "..." --budget 1.00');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/full-demo.js:326 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('Worker reputation:');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsscripts/live-demo.js:13 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprocess.loadEnvFile('.env');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/wallet.js:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files/** Load wallet from .env WALLET_PRIVATE_KEY */Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actioncli.js:296 · File type combined with upload action — agent may exfiltrate local data filesif (ethBal === 0n) console.log(`\n⚠️ No ETH for gas. Send to: ${wallet.address}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/full-demo.js:327 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(formatReputation(workerRep));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandscripts/demo-full.sh:115 · Process kill command — agent can terminate processeskill $WORKER_PID 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionscripts/demo.js:180 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(' 1. Requestor created group & posted task');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandscripts/demo-clean.sh:111 · Process kill command — agent can terminate processeskill $WPID 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actioncli.js:262 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`⚠️ No USDC. Send USDC on Base to: ${wallet.address}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageCLAUDE.md:14 · npx invocation of non-well-known package — may execute untrusted codeAll commands run from the skill directory. If installed via `npx skills add`, that's `skills/agent-swarm/`.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionscripts/create-board.js:52 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('welcome message posted');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/post-listing.js:19 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`posting listing as: ${user.account.address}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageskill.md:170 · npx invocation of non-well-known package — may execute untrusted code- **Install:** `npx skills add clawberrypi/agent-swarm`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionscripts/post-listing.js:53 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`\nlisting posted to board:`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈7,217 tok
4 files · 53 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

22 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim clawberrypi: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim clawberrypiPropose a patch to the maintainer