Back to skill

Security audit

Market Open Watch

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small market-news briefing stub that asks for public web search access and shows no evidence of hidden, destructive, persistent, or credential-related behavior.

Installers should treat this as an incomplete helper or template rather than a working market briefing tool. It appears low-risk from a security perspective, but users should verify market information independently and should not rely on it for trading decisions unless the missing search and briefing implementation is completed and reviewed.

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
  • 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 (2)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The comment at the top states 'Implementation: Uses web_search to find market news,' which directly implies an active search implementation. However, the remainder of the script only constructs a keyword and prints instructions about using web_search later, so the documentation contradicts the code's actual behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest describes a skill that provides structured briefings with market overview, key events, impacts, watchlists, and sources for Hong Kong and US stocks. In practice, this script does not perform any search or generate such a briefing; it only echoes placeholder text describing what a future integration should do.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.