Back to skill

Security audit

CheckMCC

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward CheckMCC lookup helper, with its external API use disclosed and no evidence of hidden execution, persistence, credential access, or destructive behavior.

Before installing, understand that merchant names, domains, MCCs, and region selections may be sent to check-mcc.com. For accurate results, explicitly specify SG or US until the default-region documentation is corrected, and treat rewards output as eligibility guidance rather than financial advice.

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
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill sends user-supplied merchant names and domains to an external service over HTTP, but it does not instruct the agent to disclose that data sharing to the user. Even though the data is not highly sensitive by default, merchant/domain lookups can reveal user interests, shopping behavior, or intended purchases, creating a privacy and consent issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The configuration sets the default region to US while the command documentation says omitted region defaults to SG, creating inconsistent behavior. This can cause the skill to query the wrong regional card portfolio and return misleading eligibility results, potentially disclosing incorrect financial guidance to users.

Content

No source excerpt is available for this finding.