Back to skill

Security audit

Aloudata CAN SKILLS - analysis-report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language report-generation coordinator that appears purpose-aligned and does not include hidden execution, persistence, or data exfiltration behavior.

Install this if you want a Chinese-language workflow for producing structured analysis reports. Users should still check the requested report scope and outline before allowing downstream data-analysis skills to query business data.

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
84% confidence
Finding

The manifest description and trigger definitions are written entirely in Chinese and define operation through Chinese phrases, indicating an implicit language restriction. There is no statement that users may interact in other languages or that Chinese is a justified region-specific requirement, which creates a language/locale policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes broad, everyday phrases such as '工作总结' and '总结一下上月情况' that can match normal conversational requests, causing the orchestration skill to activate when the user did not explicitly ask for a full multi-step report workflow. In a skill that coordinates multiple downstream analysis skills, accidental invocation can expand scope, consume data/tool access unnecessarily, and lead to unintended report generation or disclosure of more information than needed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.