ai-llm-agent-security

SKILLWorkflowcommunity
v0.0.0zhaji2333MITUpdated 1mo agoSource →

当目标为 LLM 应用/Chatbot/智能客服/AI 助手/Copilot/Agent/RAG 知识库/多模态模型,或发现用户输入进入大模型提示、工具调用、知识库检索、对话记忆、文件解析,或需要测试提示词注入/越狱逃逸/System Prompt 泄露/训练数据与敏感信息泄露/RAG 检索污染/Agent 记忆污染/工具滥用与命令执行/SSRF/沙箱逃逸时调用。负责 OWASP LLM Top 10 (2025) 全域深度挖掘与对抗。

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
42Repo stars
1Clients
1Formats
1mo agoLast update
Skill
Authorzhaji2333
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

当目标为 LLM 应用/Chatbot/智能客服/AI 助手/Copilot/Agent/RAG 知识库/多模态模型,或发现用户输入进入大模型提示、工具调用、知识库检索、对话记忆、文件解析,或需要测试提示词注入/越狱逃逸/System Prompt 泄露/训练数据与敏感信息泄露/RAG 检索污染/Agent 记忆污染/工具滥用与命令执行/SSRF/沙箱逃逸时调用。负责 OWASP LLM Top 10 (2025) 全域深度挖掘与对抗。

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.

Topics

Related in security