Back to skill

Security audit

Currency Exchange Rate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward currency-rate helper that uses a disclosed third-party exchange-rate API and does not show hidden persistence, credential access, or unrelated behavior.

Install only if you are comfortable with currency lookup requests being sent to exchangerate-api.com. Avoid putting sensitive business context or identifying information into currency-code arguments, and expect the command-line output to appear mostly in Chinese.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill documents network-backed functionality but does not declare an explicit tool scope such as allowed-tools or permissions. This creates a governance gap where callers may not understand that the skill can make outbound requests, reducing transparency and weakening policy enforcement around network access.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The example output uses Chinese labels like '汇率转换', '汇率', and '日期' without any indication that language is configurable or intentionally region-specific. That creates a natural-language policy concern because the skill appears to force a locale-specific output without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code presents its title, help text, errors, and command output in Chinese, starting from the module description and continuing throughout the CLI. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The skill sends user-supplied currency query context to an external third-party API, which creates a real data egress boundary. While the transmitted data is limited and the domain is hardcoded to HTTPS, use of an unauthenticated external service can expose usage metadata, leak potentially sensitive financial lookup patterns, and make results dependent on an untrusted remote source.

Content

Scanner excerpt · scripts/exchange-rate.py (reported line 14)May include surrounding context.

python
import urllib.error
from urllib.parse import quote

API_BASE = "https://api.exchangerate-api.com/v4/latest"

def fetch_json(url, timeout=15):
    """获取 JSON 数据"""

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description omits a clear notice that user-supplied currency queries are sent to a third-party service, exchangerate-api.com. Even if the data is usually low sensitivity, this is a privacy and transparency issue because users may not realize their requests leave the local environment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.