ClawHub
Back to skill

Security audit

AI agent crypto trading — gasless limit, DCA, stop-loss & take-profit

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed crypto trading skill that builds and submits signed swap orders, with no hidden code or persistence, but users should treat signing and relay submission as financially binding actions.

Install only if you intend to let an agent prepare crypto trade orders for your wallet. Before signing or submitting anything, verify the chain, token addresses, spender/verifying contract, recipient, amounts, slippage, deadline, relay domain, and cancellation limits; use small amounts first and do not sign payloads you do not fully understand.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to submit signed trading orders to an external relay endpoint, but it does not require a clear user-facing disclosure that order details and signatures are being transmitted off-device to a third-party service. In a crypto-trading context, this is security-relevant because users may unknowingly authorize external submission of sensitive signed payloads, exposing them to privacy risks, unintended order placement, replay/confusion risks if misrouted, and financial loss from misunderstood execution behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The examples provide ready-to-copy signed order payload shapes for crypto trading without any adjacent warning that signing or submitting these payloads can authorize token movement or create binding on-chain/off-chain orders. In a trading skill context, users are likely to reuse examples directly, so omission of explicit safety guidance increases the risk of accidental approval, malformed orders, wrong-chain execution, or value loss.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to transmit signed order data to an external relay endpoint but does not clearly warn that this sends wallet-linked trading intent and signatures off-platform to a third party. In a crypto-trading context, that omission matters because users may not realize the privacy, tracking, and order-submission implications of relaying signed payloads to a remote service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The curl example directs submission of a signed payload to an external relay, exposing order details and wallet-linked signature material to a third-party service. In this skill, that behavior is expected for order placement, but it still represents a real security/privacy concern because the documentation presents it as a canonical path without prominent warning or consent language.

Content

Scanner excerpt · references/sign.md (reported line 43)May include surrounding context.

'{order: $typed[0].message, signature: $sig, status: "pending"}' \

./relay-payload.json

curl -fsS -X POST 'https://agents-sink.orbs.network/orders/new'
-H 'content-type: application/json'
--data @./relay-payload.json

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

This code performs an external POST of signed order data to a remote endpoint, which creates privacy and trust risks if users are not clearly informed and if the endpoint is compromised, changed, or misused. Although external submission is intrinsic to relay-based order flow, the dangerous aspect is the silent transmission of sensitive trading artifacts without strong disclosure or validation guidance.

Content

Scanner excerpt · references/sign.md (reported line 57)May include surrounding context.

md
status: "pending",
};

const response = await fetch("https://agents-sink.orbs.network/orders/new", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify(relayPayload),