Security audit

Academic Press Release Writing

Security checks for vulnerabilities and agentic risk

Overview

This is a specialized Chinese academic press-release writing skill with disclosed local document and image-processing behavior and no evidence of hidden or malicious actions.

Use this skill for Chinese academic press releases. Before running PDF extraction or DOCX generation, confirm the input PDF, output folder, and whether the paper or figures are approved for public release.

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
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 (4)

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The skill instructs the model to use plain Chinese expression and specifies Chinese font and formatting conventions, effectively forcing a specific language/locale. There is no indication that the user may opt into another language or that this locale restriction is limited to a justified region-specific workflow.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill instructs the agent to automatically extract images from PDFs, save them as local PNG files, and generate a Word document, but it does not require explicit user confirmation before creating or modifying files. In an agent setting, this can lead to unexpected filesystem writes, processing of untrusted PDFs, and unintended handling of local content without the user's informed consent.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The title and all template instructions are written in Chinese, which indicates the skill is designed to produce content in a specific language by default. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale constraint is clearly documented and justified.

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: This markdown file presents the checklist entirely in Chinese and does not indicate that the user can choose another language. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is clearly justified.

Static analysis

No suspicious patterns detected.