ClawHub
Back to skill

Security audit

Uniswap Swap

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a disclosed Uniswap swap quoting and unsigned transaction-preparation workflow with explicit safeguards against signing, sending, or exposing secrets.

Before installing, use this only for Uniswap swap research, quoting, approval review, or unsigned handoff preparation. Confirm token addresses, chain IDs, recipient, slippage, and route before using any wallet, and never let an agent sign or submit transactions unless you explicitly authorize the exact wallet action.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables implicit invocation while the default prompt is broadly phrased to trigger on generic 'protocol task' requests, without clear boundaries for when the agent should or should not invoke this workflow. In a financial/DeFi context, that can cause the agent to initiate swap-related guidance or transaction-preparation steps inappropriately, increasing the chance of unintended trading actions, incorrect route selection, or unsafe handling of approvals such as Permit2.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/recipes.md (reported line 24)May include surrounding context.

text

```sh
curl --fail-with-body --silent --show-error 'https://trade-api.gateway.uniswap.org/v1/quote'   -H "x-api-key: $UNISWAP_API_KEY" -H 'Content-Type: application/json'   -H "x-universal-router-version: $UNISWAP_ROUTER_VERSION"   --data-binary @quote-request.json

Do not enable shell tracing. Persist response with restricted permissions if needed; API keys and signatures stay out of evidence files.

Static analysis

No suspicious patterns detected.