Back to skill

Security audit

Deal Hunting

Security checks for vulnerabilities and agentic risk

Overview

This is a simple deal-finding guidance skill with no executable code, persistence, credential handling, or hidden high-impact behavior.

Installers should understand this as a Chinese-language deal-hunting helper. It may need web searches for current prices, coupons, reviews, and sale timing, so users should verify deals and seller trust before buying, but the artifact does not ask for private accounts or unsafe permissions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The visible natural-language description, headings, and example requests are all written in Chinese, with no indication that other languages are supported or that Chinese output is optional. This can violate language/locale policy when a skill implicitly enforces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The sample trigger language uses generic phrasing such as '如何快速使用…处理 [具体场景任务]' and asks about '核心功能', which does not clearly constrain when this skill should activate versus a general shopping or help assistant. The file also provides no negative examples or explicit trigger boundaries to prevent unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.