ClawHub
Back to skill

Security audit

Crypto Market Quotes

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple cryptocurrency quote helper that calls public market-data APIs and does not request credentials, persistence, or broad local access.

Install this if you are comfortable with the agent making unauthenticated requests to public cryptocurrency data providers for the symbols you ask about. Treat returned prices as informational market data, not financial advice, and ask for a different response language if the Chinese output template is not desired.

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 (7)

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The skill title and later output templates are written in Chinese, and the document does not indicate that language is optional or user-selectable. This creates a natural-language policy concern because the skill appears to prescribe a specific locale without opt-in.

External Transmission

Medium
Category
Data Exfiltration
Content
### Single coin price (Binance)

```bash
curl -s "https://api.binance.com/api/v3/ticker/24hr?symbol=BTCUSDT"
```

Key response fields:
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
### Single coin price (Binance)

```bash
curl -s "https://api.binance.com/api/v3/ticker/24hr?symbol=BTCUSDT"
```

Key response fields:
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
### Single coin price (Binance)

```bash
curl -s "https://api.binance.com/api/v3/ticker/24hr?symbol=BTCUSDT"
```

Key response fields:
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
### Top coins by market cap (CoinGecko, no key needed)

```bash
curl -s "https://api.coingecko.com/api/v3/coins/markets?vs_currency=usd&order=market_cap_desc&per_page=20&page=1&sparkline=false"
```

Features: includes market_cap, total_volume, circulating_supply, ath (all-time high), ath_change_percentage, atl, image (icon URL)
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
### Kraken ticker

```bash
curl -s "https://api.kraken.com/0/public/Ticker?pair=XBTUSD"
```

## Supported Coins (Binance)
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The 'Format Output' examples specify Chinese headings and field labels for the skill's responses, which implies a fixed output locale. Because no user choice or region-specific justification is provided, this is a policy violation under language/locale constraints.

Static analysis

No suspicious patterns detected.