Security audit
强制进度检查点。当龙虾助手在执行任务时超过60秒没有完成，必须立即向用户发送进度反馈，说明：任务是否正常运行、当前执行到哪个步骤、预计还要多久。用于防止用户对长时间运行任务的不确定感。 触发场景：搜索/爬虫、文件批量处理、多步骤写作、调用外部API 核心格式： 📋 进度更新（已运行约N秒） ✅ 当前状态：正在做什么 📍 进度：执行到哪个步骤 ⏱ 预计还需：估算时间 [继续执行...]
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only skill that asks the agent to give progress updates during long tasks, with no code execution, data access, or persistence.
Install this if you want the agent to proactively report status during longer tasks. The main tradeoff is behavioral: it may interrupt work with progress messages, and its priority language should be treated as a preference within normal platform and user-instruction boundaries.
SkillSpector
By NVIDIA
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.