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
技能升级巧匠L2
Security checks for vulnerabilities and agentic risk
Overview
This is a markdown-only Chinese skill for improving other skill prompts, with no hidden execution, credential access, network use, or persistence.
Install this if you want a Chinese-language assistant for improving existing Skill.md files. Review and possibly narrow the trigger phrases before using it in a large shared skill set, and expect it to produce proposed skill text rather than automatically modify other skills.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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
Findings (7)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
This markdown file contains user-facing deployment instructions exclusively in Chinese, and nowhere indicates that users may choose another language or that the locale restriction is intentional. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The trigger set contains broad phrases such as requests about fixing a skill or repairing entry behavior, which can overlap with many ordinary support or editing requests. In a multi-skill environment, overly general triggers can cause unintended routing, skill hijacking, or collisions with adjacent skills, leading to incorrect execution paths and unstable behavior.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 86% confidence
- Finding
The trigger phrase at this location is vague enough to resemble common everyday speech, increasing the chance that normal user requests accidentally invoke this skill. In a shared agent ecosystem, such ambiguity can crowd out more appropriate skills and create denial-of-service-like routing instability for legitimate specialized workflows.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The entire test prompt file is written as if the skill and its evaluations should operate in Chinese only, with no indication that users may choose another language or locale. Under the policy rule, forcing a specific language without offering a choice is a natural-language policy violation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This markdown validation report presents all user-facing natural language in a single forced language/locale. Under the policy, language constraints should either offer user opt-in/choice or be clearly documented as justified for a region-specific use case, which is not present here.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 80% confidence
- Finding
The instruction "frontmatter 中统一中文名，英文名降级为 alias" imposes a Chinese-language naming policy as a default requirement. The file does not indicate user choice, opt-in, or a documented region-specific justification for this locale constraint.
- Content