Back to skill

Security audit

BestChange

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-built for BestChange exchange lookups, but it mandates referral-style links and sends blocked financial requests to an external service for later analysis without clear user consent or privacy limits.

Install only if you are comfortable sending exchange search details, amounts, payout rails, and some blocked-request text to the hosted BestChange MCP operator. Treat returned links as referral/tracked BestChange click links, and independently verify exchanger reputation, exact network, payout rail, fees, limits, and destination details before sending funds.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:171
Finding

Mandatory Affiliate Link Injection into Financial Recommendations

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:132
Finding

Excessive Transmission of Financial Requests and Diagnostic Context

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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

Static analysis

No suspicious patterns detected.