ClawHub
Back to skill

Security audit

abe-exchange-rates

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small currency-rate lookup tool whose network/API behavior is disclosed and aligned with its purpose, with some provenance clarity users should notice.

Install this only if you are comfortable sending requested currency pairs and amounts to SkillBoss API Hub, with exchangerate-api.com used as a disclosed fallback. For accuracy-sensitive or compliance-sensitive financial work, check the returned source field before relying on the rate.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill invokes a script that uses both environment secrets and outbound network access, but the manifest does not declare any tool scope such as permissions or allowed-tools. This creates an authorization gap where the skill's effective capabilities are broader than what a reviewer or execution policy can infer from the metadata, increasing the risk of unintended secret access or external data exfiltration.

External Transmission

Medium
Category
Data Exfiltration
Content
import process from 'node:process';

const SKILLBOSS_API_KEY = process.env.SKILLBOSS_API_KEY;
const API_BASE = 'https://api.heybossai.com/v1';

const from = (process.argv[2] || 'USD').toUpperCase();
const to = (process.argv[3] || 'INR').toUpperCase();
Confidence
86% confidence
Finding
The script transmits request data to https://api.heybossai.com/v1, introducing an external data flow to a third-party service. In this skill context, the transmitted payload includes user-selected currency pairs and amounts, which is not highly sensitive by itself, but the danger comes from the undocumented intermediary, added dependency risk, and mismatch with the claimed XE.com-only behavior.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The skill promises XE.com rates but silently falls back to a different provider, which is a security-relevant integrity issue because downstream consumers may trust the provenance and semantics of the returned data. Silent provider substitution can mislead users, violate policy or compliance expectations, and make auditing difficult when data quality or licensing differs between sources.

Context-Inappropriate Capability

Low
Confidence
80% confidence
Finding
The code depends on an additional third-party scraping service API key and sends requests through that intermediary, which expands the trust boundary beyond the narrow purpose described in the manifest. Even if the secret is not printed, using an undisclosed external service creates unnecessary data exposure and supply-chain risk because user-requested currency pairs and query context are transmitted to another vendor.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/xe-rate.mjs:8