ClawHub
Back to skill

Security audit

Stripe Cli

Security checks for vulnerabilities and agentic risk

Overview

This Stripe CLI skill is coherent and disclosed, with reasonable safeguards for sandbox-first Stripe development workflows.

Install only if you intend to let your agent help with Stripe CLI development tasks. Keep it in test/sandbox mode by default, verify the active Stripe account before commands that create or update resources, avoid live keys unless you explicitly approve the action, and review any non-local webhook forwarding target before running the listener script.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
Findings (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The declared description centers on operational use of the Stripe CLI for development and sandbox testing workflows. The actual code does not invoke the Stripe CLI, manage webhooks, trigger events, inspect API requests, or perform sandbox resource management. Instead, it sanitizes logs or text by masking Stripe-related secrets. While this is Stripe-related and could support safe log handling, it is a materially different primary purpose that is not represented in the description.