Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
L003 使用了“用户要求诊断简历质量；用户想优化简历; 用户问我的简历有什么问题”这类自然语言触发描述，但没有限定具体触发短语、上下文约束或不触发的反例。诸如“优化简历”“我的简历有什么问题”与日常对话高度接近，容易导致技能被宽泛匹配或误触发。
- Content
Security audit
51mee Resume Diagnose
Security checks for vulnerabilities and agentic risk
Overview
This skill only reads a user-provided resume to generate a structured resume diagnosis, with no evidence of hidden execution, persistence, or unrelated data access.
Installers should expect the skill to process resume contents, which may include personal information. Use it only with resumes the user intentionally provides, and consider improving the trigger wording and language handling, but no security hold is supported by the artifacts inspected.
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
- 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 (2)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
L025-L029 的提示词以及整份技能说明均固定为中文输出要求，没有说明可根据用户语言偏好切换，也未提供语言/locale 选择。根据规则，强制特定语言而无用户 opt-in 属于自然语言政策问题。
- Content
Static analysis
No suspicious patterns detected.