Back to skill

Security audit

payment-processor

Security checks for vulnerabilities and agentic risk

Overview

This payment-processing skill is very under-specified for a high-impact financial workflow and asks for an API key without clear safeguards.

Review this carefully before installing. It is not malicious from the inspected text, but it is too vague for payment operations: require explicit user authorization before any charge/refund/account action, use least-privilege test credentials first, avoid raw card data unless a compliant tokenization flow is documented, and do not route secrets or payment details through logs or generic input/output files.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The documentation describes payment processing and API key configuration but does not warn about handling payment data, protecting credentials, or avoiding exposure of sensitive information in inputs, outputs, and logs. In a payments skill, this omission is especially dangerous because operators or downstream agents may pass cardholder data or secrets insecurely, creating a path to credential leakage, compliance violations, or fraudulent transactions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s description and usage criteria are broad enough that an agent could invoke it for loosely related 'process tasks' or generic ecommerce operations without clear boundaries. In a payment-processing context, ambiguous triggering increases the chance of handling sensitive financial workflows in inappropriate situations, which can lead to unauthorized payment actions or misuse of credentials.

Content

No source excerpt is available for this finding.