ClawHub
Back to skill

Security audit

Stripe

Security checks for vulnerabilities and agentic risk

Overview

This Stripe skill is mostly coherent, but it needs review because it can change or delete Stripe data and includes unsafe remote-script install instructions.

Install only if you trust OOMOL to mediate Stripe access, and treat all write or delete actions as real Stripe account changes that require explicit review. Avoid running the one-line remote installer commands blindly; prefer an official, verifiable oo CLI installation path before using the skill.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (4)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

curl ... | bash is a classic unsafe pattern because it executes remote content immediately without inspection or verification. In this skill context, the command is presented as a troubleshooting step, making it more likely an agent or user may run it reflexively, turning a documentation issue into a direct arbitrary code execution risk.

Content

Scanner excerpt · SKILL.md (reported line 72)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The instruction to use this skill for ANY Stripe request is overly broad and can cause an agent to invoke the skill automatically whenever Stripe is mentioned, including in ambiguous or adversarial contexts. Because the skill supports write and destructive actions, broad routing increases the chance of unintended state-changing operations being selected without sufficient task scoping.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The setup guidance recommends installing software by piping a remotely fetched script directly into a shell, without warning the user about the trust implications or suggesting integrity verification. If the remote host, distribution path, or network path were compromised, this could lead to arbitrary code execution on the user's machine.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

At L56, update_price is tagged [destructive], but its description says it only updates mutable fields on a Stripe price, which does not match the ordinary meaning of destructive removal or overwrite. The safety section at L63 then instructs stronger handling for [destructive] actions, so the documentation contradicts the actual stated behavior of the action.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.