ClawHub
Back to skill

Security audit

DeFi Position Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed DeFi portfolio-analysis guide that uses external portfolio APIs but does not include hidden execution, transaction signing, persistence, or destructive behavior.

Before installing, be aware that using the example commands can reveal wallet addresses, position IDs, portfolio details, and API keys to third-party DeFi data providers. Use read-only API keys where possible, review provider terms, and do not supply wallet private keys or seed phrases.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

External Transmission

Medium
Category
Data Exfiltration
Content
**Free alternative — Zapper API:**
```bash
curl -s "https://api.zapper.xyz/v2/balances?addresses[]=0xYOUR_WALLET&networks[]=ethereum&networks[]=arbitrum" \
  -H "Authorization: Basic $(echo -n ':YOUR_ZAPPER_KEY' | base64)"
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
Uniswap v3 IL is range-dependent. Use the official SDK or Revert Finance API:
```bash
# Revert Finance — v3 position analytics
curl "https://api.revert.finance/v1/position?position_id=YOUR_NFT_ID&chain_id=1"
```

### 3. Cost Basis Tracking Per Position
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
Uniswap v3 IL is range-dependent. Use the official SDK or Revert Finance API:
```bash
# Revert Finance — v3 position analytics
curl "https://api.revert.finance/v1/position?position_id=YOUR_NFT_ID&chain_id=1"
```

### 3. Cost Basis Tracking Per Position
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# Pull staking reward history via The Graph (Lido example)
curl -X POST "https://api.thegraph.com/subgraphs/name/lidofinance/lido" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "{ totalRewards(where: {account: \"0xYOUR_WALLET\"}, orderBy: block, orderDirection: desc, first: 100) { id totalRewards totalFee block blockTime } }"
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# Pull staking reward history via The Graph (Lido example)
curl -X POST "https://api.thegraph.com/subgraphs/name/lidofinance/lido" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "{ totalRewards(where: {account: \"0xYOUR_WALLET\"}, orderBy: block, orderDirection: desc, first: 100) { id totalRewards totalFee block blockTime } }"
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Description-Behavior Mismatch

Low
Confidence
77% confidence
Finding
The manifest focuses on tracking and analytics outputs for reporting, tax handoff, and dashboards, and explicitly says the skill is not for real-time price alerts on spot holdings without active DeFi positions. The 'Monitoring & Alerts' section adds operational alerting behavior, including health-factor thresholds and out-of-range detection, which extends beyond the described reporting-oriented scope even if related to DeFi positions.

Context-Inappropriate Capability

Low
Confidence
72% confidence
Finding
The manifest states the skill 'outputs structured data for portfolio reporting, tax handoff ... and treasury dashboards.' In contrast, the workflow explicitly says to 'Generate markdown summary for treasury dashboard,' which adds a presentation/content-generation capability not clearly justified by the stated structured-data purpose.

Static analysis

No suspicious patterns detected.