Back to skill

Security audit

Groww

Security checks for vulnerabilities and agentic risk

Overview

This skill is clearly for Groww stock trading, but it gives an agent live order-placement and cancellation paths without documented confirmation safeguards.

Install only if you intend to let an agent access your Groww account and potentially place or cancel trades. Use a restricted key if Groww supports it, keep trading disabled unless needed, and require explicit human confirmation for every buy, sell, or cancel request.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (12)

Credential Access

High
Category
Privilege Escalation
Content
## Setup

1. Get API key from Groww app: Stocks → Settings → API Trading → Generate API key
2. Add to OpenClaw config:
   ```bash
   openclaw configure
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill documents direct order placement and cancellation flows, including market orders, without requiring explicit user confirmation, order-parameter verification, or any warning about irreversible financial consequences. In an agent setting, this increases the chance of unintended or prompt-induced trades, making the skill materially riskier than a read-only market-data integration.

External Transmission

Medium
Category
Data Exfiltration
Content
### Base URL
```
https://api.groww.in/v1/
```

### Headers
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### Base URL
```
https://api.groww.in/v1/
```

### Headers
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### Base URL
```
https://api.groww.in/v1/
```

### Headers
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### Base URL
```
https://api.groww.in/v1/
```

### Headers
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### Base URL
```
https://api.groww.in/v1/
```

### Headers
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### Base URL
```
https://api.groww.in/v1/
```

### Headers
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### Base URL
```
https://api.groww.in/v1/
```

### Headers
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
**Portfolio/Holdings:**
```bash
curl -H "Authorization: Bearer $GROWW_API_KEY" -H "Accept: application/json" \
  "https://api.groww.in/v1/holdings/user"
```
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
curl -X POST -H "Authorization: Bearer $GROWW_API_KEY" \
  -H "Accept: application/json" -H "Content-Type: application/json" \
  -d '{"trading_symbol":"TATAMOTORS","quantity":10,"validity":"DAY","exchange":"NSE","segment":"CASH","product":"CNC","order_type":"MARKET","transaction_type":"BUY"}' \
  "https://api.groww.in/v1/order/create"
```

**Order Status:**
Confidence
78% confidence
Finding
Unlike the read-only endpoints, this external transmission creates a live trade using an authenticated brokerage token. In the context of an autonomous or semi-autonomous agent, documenting a direct order-creation call without enforced confirmation or guardrails materially raises the risk of unauthorized or accidental financial transactions.

External Transmission

Medium
Category
Data Exfiltration
Content
curl -X POST -H "Authorization: Bearer $GROWW_API_KEY" \
  -H "Accept: application/json" -H "Content-Type: application/json" \
  -d '{"segment":"CASH","groww_order_id":"ABC123"}' \
  "https://api.groww.in/v1/order/cancel"
```

## Stock Symbols
Confidence
76% confidence
Finding
This authenticated external transmission cancels an order, which is a state-changing account action with possible financial consequences. In an agent skill, presenting a direct cancellation call without mandatory confirmation or anti-abuse controls can lead to unauthorized disruption of user trading activity.

Static analysis

No suspicious patterns detected.