Back to skill

Security audit

Market News Aggregator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a benign market-news summarizer for public Chinese financial sources, with minor usability caveats around Chinese-only formatting and a referenced script that is not included.

Installers should understand that the skill fetches public market-news pages and may produce Chinese-formatted financial summaries by default. It should not be treated as investment advice, and users who need another language or exact source verification should request that explicitly.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The overview and subsequent instructions are written as mandatory Chinese output behavior, and the formatting rules later explicitly require Chinese summaries and labels. This creates a locale/language constraint without any stated user choice or opt-in, which matches the language-policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The summary step requires each item to be 20-40 Chinese characters, which operationalizes a mandatory Chinese-only response format. Because no alternative language option is offered or documented, this is a natural-language policy issue rather than a content preference.

Content

No source excerpt is available for this finding.