Back to skill

Security audit

India Stock Market Pulse

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed market-briefing and alert helper whose external data access, watchlist storage, and optional scheduled delivery fit its stated purpose.

Before installing, understand that your watchlist and alerts may persist in OpenClaw configuration or memory, and scheduled briefings or triggered alerts may be sent through your active messaging channel. Use explicit commands for alerts and review cron jobs if you enable automated delivery.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill advertises automated delivery via WhatsApp or Telegram and stores watchlist/alert data, but it does not prominently warn users that preferences and alerts persist and may be sent outbound automatically. This creates a consent and privacy risk: users may not realize their financial interests or alert activity are being retained and transmitted through external messaging channels.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.

md
Use the following free public APIs — no API key required:
- **NSE India (unofficial)**: `https://www.nseindia.com/api/` — use browser headers to avoid blocking
- **Yahoo Finance India**: `https://query1.finance.yahoo.com/v8/finance/chart/{SYMBOL}.NS` for NSE stocks
- **BSE India**: `https://api.bseindia.com/BseIndiaAPI/api/` for BSE data
- **Moneycontrol RSS**: `https://www.moneycontrol.com/rss/latestnews.xml` for headlines

For Yahoo Finance, append `.NS` for NSE stocks (e.g. `RELIANCE.NS`) and `.BO` for BSE.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manual trigger phrase "pulse" is generic enough to collide with ordinary user conversation, especially in a chat environment where users may use the word in unrelated contexts. That can cause the skill to activate unexpectedly and fetch/send market data or perform stateful actions when the user did not intend to invoke it.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.