ClawHub
Back to skill

Security audit

exchange-rate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward currency exchange-rate helper that makes disclosed API requests and does not show hidden persistence, credential use, or destructive behavior.

Before installing, note that this skill needs outbound network access to Frankfurter for exchange-rate data and may trigger on broad currency terms. It does not require an API key and I found no hidden persistence, credential handling, or destructive actions.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.

md
2. Run `bun scripts/exchange.ts --help` in this skill directory.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill instructs the agent to run a network-capable script (bun scripts/exchange.ts) but does not declare any explicit tool scope such as permissions or allowed-tools. That creates an authorization gap where the skill's actual capability surface is broader than what its manifest communicates, increasing the risk of unintended or over-privileged network access.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad everyday terms like currency names (美元, 欧元, USD, EUR, etc.) and generic phrasing patterns that may appear in ordinary conversation outside an explicit exchange-rate request. This can cause unintended invocation of the skill, which is especially relevant here because invocation may lead to command execution and outbound network requests.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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/command-map.md (reported line 30)May include surrounding context.

md
export const API_BASE_URL = "https://api.frankfurter.dev/v1";

export const DEFAULT_TIMEOUT_MS = 15_000;
export const DEFAULT_RETRY_COUNT = 2;

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · scripts/lib/config.ts (reported line 1)May include surrounding context.

ts
export const API_BASE_URL = "https://api.frankfurter.dev/v1";

export const DEFAULT_TIMEOUT_MS = 15_000;
export const DEFAULT_RETRY_COUNT = 2;

Static analysis

No suspicious patterns detected.