Security audit

论文报告验真教程

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped Chinese tutorial for verifying plagiarism/AIGC report authenticity through official portals, with clear limits against collecting credentials, submitting forms, or storing user data.

Install this if you want step-by-step Chinese guidance for verifying report authenticity through the listed official portals. Users should still avoid sharing full reports or credentials, enter CAPTCHAs themselves, and confirm the current official page before submitting any report identifier.

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

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 (1)

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: Line L003 says the tutorial is for common questions like '报告是真的吗' and '报告编号在哪里', which are broad help-seeking phrases that could overlap with many routine support interactions. The file does not pair these examples with explicit limits or negative examples clarifying when this tutorial should not be used.
Content: No source excerpt is available for this finding.