# ai-llm-agent-security

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。

- **Type:** Agent Skill
- **Trust:** 10/100 (F), scored on the remote rubric — Limited: the scan came back clean but coverage was partial, so the score sits below what full coverage would allow. Nothing was found.
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.0.0
- **Author:** zhaji2333
- **License:** MIT
- **Source:** https://github.com/zhaji2333/CkSKILLS/tree/main/.agents/skills/ai-llm-agent-security

## Trust

10/100 (F), scored on the remote rubric — Limited: the scan came back clean but coverage was partial, so the score sits below what full coverage would allow. Nothing was found.
- Publisher verified: no
- Install scripts: not scanned
- Prompt-injection scan: not run
- Obfuscation scan: not run

## Security scan

Not scanned. This is a coverage gap, not a clean result — Forge asserts nothing about this entry's security posture.

## Install

This is an Agent Skill — a prompt, not an MCP server, so there is no client config to generate. Fetch it with forge_get_skill and install it with forge_add_skill.

## Blast radius

Contained blast radius — runs as a prompt.
- Floor 4, ceiling 4 (tier: contained)
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/ai-llm-agent-security
- Install plan: https://forgeregistry.com/api/v1/packages/ai-llm-agent-security/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/ai-llm-agent-security
- HTML page: https://forgeregistry.com/registry/ai-llm-agent-security
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.