Security audit

gov-doc-skill

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Chinese government-document drafting assistant, but it invites use with internal and classified government materials without adequate data-handling boundaries.

Install only if users will provide non-sensitive or properly redacted materials, or if the skill runs in an approved secure environment for government work. Do not paste classified, internal-only, personal, or unpublished leadership materials into a general hosted model despite the skill's confidentiality fields.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The README explicitly encourages users to upload detailed source materials such as internal data, work progress, problem lists, leadership instructions, and prior drafts, but provides no warning, filtering guidance, or confidentiality controls. In a government-document drafting context, those materials are very likely to contain non-public, sensitive, or classified information, so this creates a real risk of improper disclosure to the model or downstream platform.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The skill is written entirely in Chinese and presents itself as a Chinese government-document drafting expert without offering any user choice of language or locale. This can override user preferences, reduce accessibility, and cause inappropriate assumptions about jurisdiction, legal style, and audience, especially if invoked in multilingual or non-Chinese contexts.

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The description states this is a government document writing test case set in Chinese ("政府公文写作技能测试用例"), and the examples and validation rules consistently require Chinese-specific forms of address and output structure. Because the file provides no indication that users may choose another language or locale, it imposes a language/locale constraint without opt-in.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The title and description frame the knowledge base as authoritative guidance for AI writing of government documents entirely in Chinese, and the file provides no indication that language choice is optional. Under the policy rule, forcing a specific language or locale without user opt-in is a natural-language policy concern unless the constraint is explicitly justified as region-specific.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The file defines all output templates in Chinese and presents them as the required output format, without any indication that language choice depends on user preference or locale. In an agent skill, this can override user intent, reduce accessibility, and cause policy or usability failures when users expect another language or a locale-neutral response.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The natural-language description is entirely in Chinese and positions the skill as a government document writing expert for Chinese official materials, but it does not state that the locale/language limitation is optional or user-selectable. Under the policy rule, forcing a specific language without opt-in is a locale policy concern unless the regional constraint is explicitly documented and justified.

Natural-Language Policy Violations

Low

Confidence: 83% confidence
Finding: The entire skill description is written as a Chinese-only experience for government document drafting, with no indication that users may choose another language or that the locale restriction is explicitly intentional and documented. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Static analysis

No suspicious patterns detected.