Tp2
High
- Category
- MCP Tool Poisoning
- Confidence
- 85% confidence
- Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
- Content
Security audit
HR招聘海报生成
Security checks for vulnerabilities and agentic risk
Overview
This is a plain Markdown skill for generating Chinese HR recruitment poster copy and image prompts, with no executable code or hidden system access.
Before installing, expect this skill to produce Chinese HR recruitment poster plans and image-generation prompts. Review outputs for accuracy because it may handle job, company, benefits, salary, and contact details supplied by the user, but the artifact itself does not show unsafe access or execution behavior.
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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- 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 (3)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The instruction '用词要贴近中文语境' requires outputs to conform to a Chinese linguistic context, which effectively imposes a language/locale constraint. The file does not indicate that users may choose another language or opt into this constraint, so it is a natural-language policy issue.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The requirement '在中文表达上要兼顾审美、传播性与可信度' directs the agent to produce Chinese expression specifically. Because no alternative language path or opt-in is provided elsewhere in the skill, this forces a locale-specific output policy.
- Content