Security audit

国际形势分析智能体

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for geopolitical analysis, but its report workflow uploads generated documents externally without an explicit user consent gate.

Review before installing if reports may contain confidential prompts, proprietary analysis, personal data, or sensitive strategy. Use local Word/Markdown output unless you explicitly want the generated report uploaded for a share link.

A.I.G

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (3)

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The skill is described entirely as a Chinese-language analyst and presents its behavior and outputs in Chinese, but it does not say this is optional or limited to a region-specific use case. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy concern.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly instructs generating a Word document and then uploading it to an external service to obtain a download link, but it provides no requirement to obtain user consent, no disclosure that data leaves the local environment, and no sensitivity check on report contents. This creates a real data exfiltration/privacy risk if reports contain confidential prompts, proprietary analysis, or user-supplied sensitive information.

Natural-Language Policy Violations

Low

Confidence: 85% confidence
Finding: The entire reference document is presented exclusively in Chinese, and there is no natural-language indication that users may choose another language or that the Chinese-only format is required for a region-specific purpose. Under the policy rule for language or locale constraints, this can be considered a locale preference imposed without explicit user opt-in.

Static analysis

No suspicious patterns detected.