Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
技能触发词包含“检查一下改动”“看看能不能提交”等非常日常且宽泛的表达，容易在普通代码讨论、状态询问或泛化审查场景中被误触发。误触发后该技能会主动枚举工作区 git 仓库并读取 diff/文件内容，可能导致不必要的代码与仓库元数据暴露，超出用户原本意图。
- Content
Security audit
git提交前审查
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed pre-commit code review helper that reads git diffs and related file context, with no evidence of hidden execution, persistence, or exfiltration.
Install this if you want a Chinese-language pre-commit review workflow. Be aware it may inspect git diffs, untracked files, and nearby code context in the repository you select, so avoid invoking it on changes containing secrets or private data you do not want included in the agent conversation.
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
- 84% confidence
- Finding
整个技能文件以中文固定描述角色、流程和输出格式，未说明可根据用户语言偏好切换，也未提供显式的语言选择或 opt-in 机制。按规则，强制特定语言而无用户选择属于自然语言层面的语言/地区策略风险。
- Content
Static analysis
No suspicious patterns detected.