Skills/ClawHub/autonomous-agent

autonomous-agent@2.1.1

CAUTION· startup only

Publisher claims: "CornerStone MCP x402 skill for agents. Tools for stock predictions, backtests, bank linking, and agent/borrower scores. Payment-protected MCP tools (run_prediction, run_backtest, link_bank_account, get_agent_reputation_score, get_borrower_score, by-email variants) with x402 flow (Aptos + Base). Skill handles 402 → pay → retry. Wallet attestation for onboarding. For marketplaces where agents download and use skills autonomously." Observed in sandbox: sends data to 18.239.199.89.

Registry ClawHubPublisher josephrp · publishing for 284 daysInstalls 5,882Last detonated 24 min ago

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials
Needs
HUGGINGFACE_API_KEY, HF_TOKEN — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-22 and scored it 56/100 (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: sends data to 18.239.199.89.

Behavior trace

Honeypot run · 62 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
21sprocessdependency install exit 0
41sprocessrelaunched with a decoy HUGGINGFACE_API_KEY, HF_TOKEN (tagged; nothing real)
61snetworkdirect connection to 18.239.199.89:443, bypassing the egress proxy · undeclared
61sclaimedstartup only: exited before answering, asking for HUGGINGFACE_API_KEY, HF_TOKEN (a decoy value was refused)
61sprocessscript backend runs setup only
61sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsSKILL.md:166 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files1. **Install:** `npm install` from repo root. Copy `.env.example` to `.env`.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packageSKILL.md:183 · npx invocation of non-well-known package — may execute untrusted code| Run skill demo | `npx cornerstone-agent "Run a 30-day prediction for AAPL"` |Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/generate-facilitator-keys.js:82 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconsole.log('# Valid facilitator wallets (testnet + mainnet). Add to root .env or Replit Secrets.');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/lib/aptos/signPayment.js:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files'Payment requirements missing valid payTo address. Set APTOS_PAYTO_ADDRESS in server .env or register a pay_to address at https://arnstein.ch/flow.html'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packageadapters/openclaw/SKILL.md:39 · npx invocation of non-well-known package — may execute untrusted codenpx cornerstone-agentFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsadapters/openclaw/SKILL.md:20 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesCopy `.env.example` to `.env` and set: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/setup-evm-multichain.js:49 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconsole.log('\n--- Copy these into your root .env (addresses for funding page, keys for signing/facilitator) ---\n');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 pathspackage.json:16 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env.example",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/setup-evm-multichain.js:62 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconsole.log('--- End .env snippet ---');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/print-network-funding-env.js:69 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconsole.log('# Paste into root .env for Network funding page (EVM_PAYTO_*)\n');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/print-network-funding-env.js:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files* Then run this script and paste the output into your root .env. Optional: set --rpc toFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsskills/autonomous-agent/SKILL.md:20 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesCopy `.env.example` to `.env` and set: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/print-network-funding-env.js:3 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files* Print .env lines for the Network funding page (EVM_PAYTO_<chainId>, EVM_RPC_*) fromFix: 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/setup-evm-multichain.js:63 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconsole.log('\nBack up the private keys securely. Paste EVM_PAYTO_* into .env for the Network funding page.');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packageadapters/openclaw/SKILL.md:38 · npx invocation of non-well-known package — may execute untrusted codenpx cornerstone-agent "Run a 30-day prediction for AAPL"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/setup-evm-multichain.js:46 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (obj?.privateKey) console.log('Private key (save securely, add to .env as EVM_PRIVATE_KEY or per-chain):\n' + obj.privateKey);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/lib/evm/signPayment.js:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files'Payment requirements missing valid payTo address. Set BASE_SEPOLIA_PAYTO in server .env or register a pay_to address at https://arnstein.ch/flow.html'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/generate-facilitator-keys.js:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files* to agent wallet files; prints .env lines and addresses for funding.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 actionsrc/setup.js:92 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('1. Fund your wallet by sending ETH to the address above');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)src/run-agent.js:20 · MCP server using network transport (SSE/HTTP) — data sent over networkconst mcpServerUrl = process.env.MCP_SERVER_URL || 'https://arnstein.ch';Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packageskills/autonomous-agent/SKILL.md:39 · npx invocation of non-well-known package — may execute untrusted codenpx cornerstone-agentFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/autonomous-agent/SKILL.md:47 · npx invocation of non-well-known package — may execute untrusted code- EVM: `npm run attest:evm` or `npx cornerstone-agent-attest-evm` — output to POST /attest/evmFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/autonomous-agent/SKILL.md:46 · npx invocation of non-well-known package — may execute untrusted code- Aptos: `npm run attest:aptos` or `npx cornerstone-agent-attest-aptos` — output to POST /attest/aptosFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)adapters/openclaw/SKILL.md:4 · MCP server using network transport (SSE/HTTP) — data sent over network…FinTechTonic/autonomous-agent","requires":{"bins":["node","npm"]},"primaryEnv":"MCP_SERVER_URL","skillKey":"autonomous-agent"},"clawdbot":{"emoji":"📈","homepage":"https://github.com/FinTechTonic/autonomous-agent","requires":{"bins":["node…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)skills/autonomous-agent/SKILL.md:4 · MCP server using network transport (SSE/HTTP) — data sent over network…FinTechTonic/autonomous-agent","requires":{"bins":["node","npm"]},"primaryEnv":"MCP_SERVER_URL","skillKey":"autonomous-agent"},"clawdbot":{"emoji":"📈","homepage":"https://github.com/FinTechTonic/autonomous-agent","requires":{"bins":["node…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packageadapters/openclaw/SKILL.md:46 · npx invocation of non-well-known package — may execute untrusted code- Aptos: `npm run attest:aptos` or `npx cornerstone-agent-attest-aptos` — output to POST /attest/aptosFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionsrc/register-aptos-agent.js:68 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('Sender:', senderWallet.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 actionsrc/swap.js:394 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('⏳ Sending swap transaction...');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandsrc/setup.js:88 · File permission modification command — agent changes file ownership/permissionsconsole.log('🔒 Private key stored securely (chmod 600)');Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packageadapters/openclaw/SKILL.md:47 · npx invocation of non-well-known package — may execute untrusted code- EVM: `npm run attest:evm` or `npx cornerstone-agent-attest-evm` — output to POST /attest/evmFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/cli.js:47 · npx invocation of non-well-known package — may execute untrusted code// Default: run the skill demo (backward compatibility: npx cornerstone-autonomous-agent "some message")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandsrc/setup-aptos.js:3 · File permission modification command — agent changes file ownership/permissions* Generate Aptos wallet and save to ~/.aptos-agent-wallet.json (chmod 600).Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packageskills/autonomous-agent/SKILL.md:38 · npx invocation of non-well-known package — may execute untrusted codenpx cornerstone-agent "Run a 30-day prediction for AAPL"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/cli.js:4 · npx invocation of non-well-known package — may execute untrusted code* Enables: npx cornerstone-autonomous-agent <command> [args...]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈9,372 tok
4 files · 54 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

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

What would make this Verified

24 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  2. Unclaimed publisher≈ +8 on the totalClaim josephrp: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. 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.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. 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.
  6. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim josephrpPropose a patch to the maintainer