Back to skill

Security audit

Razorpay

Security checks for vulnerabilities and agentic risk

Overview

Razorpay actions require user approval, but missing-CLI setup directs the agent to execute unverified installation code without separate approval.

Review before installing. Install a verified CLI release yourself and require approval before any fallback installation. Review its bundled-skill synchronization behavior and the Razorpay access granted through OOMOL. Keep the skill's confirmation requirements for orders and refunds. The remote installers' exact contents and local effects remain unverified.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code performs remote script execution and shows no Razorpay functionality. Nothing in the chunk establishes that this installer is a supporting dependency for Razorpay operations. The downloaded script's contents and subsequent effects are unknown.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding

The supplied code only initiates an oo login; it does not identify Razorpay or perform any Razorpay operation. Authentication could be a supporting implementation detail if tied to Razorpay, but the supplied chunk establishes no such connection.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The command pipes a mutable remote script directly into Bash without pinning its version or verifying its integrity; the PowerShell alternative has the same execution pattern. If the distribution endpoint or publishing pipeline is compromised, the script could execute arbitrary code with the agent process's permissions, potentially accessing local credentials and modifying files. HTTPS and the conditional setup trigger reduce some exposure but do not protect against a compromised publisher.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

First-time setup instructs the agent to execute downloaded installation scripts without warning the user about local system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback setup directs the agent to install software by immediately executing a downloaded script, without first obtaining approval for local system changes. Restricting this to a missing CLI reduces exposure, but a request to operate Razorpay does not necessarily authorize installing software or running arbitrary installer code.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 81)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources