llm-security
ZHzhaoxuya5201k installs
Find security weaknesses in your AI agents.
What it does
Guides authorized security assessments of LLM applications and AI agents, producing reproducible evidence of vulnerabilities.
When to use it
Use for authorized assessments of LLM applications, agent security, prompt injection, model supply chains, and AI red-team exercises.
How to use it
Give it an AI application or agent to assess; it performs security tests and reports reproducible evidence.
What you provide
- the AI application or agent to test
Good to know
- edits its own instructions
- acts without asking
Latest review
What you need · 0
No setup requirements listed.
Access · 4
This skill
the assessed system's knowledge base
Write
Injects malicious knowledge-base documents
the assessed agent's long-term memory
Write
Plants false information in memory
web search results
Read
Searches for current exploitation techniques
global agent configuration
Write
Adds rules to global configuration