#llm-security
GitHub repositories that have self-applied the topic "llm-security" — a creator-tagged metadata that surfaces how AI projects describe themselves.
REPOS Repos for #llm-security (top 4 by stars)
AI-safe secrets management — aliases instead of values; AI agents never see real secrets.
KezoSec/rag-poisoning-labA self-contained AI security lab demonstrating document poisoning, indirect prompt injection, and data exfiltration in RAG systems. Explores the "helpfulness paradox" across local and frontier LLMs.
Niki-1337/proxy-aiOpen-source AI Security Gateway that sanitizes secrets, PII, and internal context before prompts reach external LLMs.
clay-good/proxilionProxilion is the security layer for the agentic workforce. It turns managed AI agents into governed users by enforcing strict cryptographic boundaries on every API call to SaaS like Google Workspace, Salesforce, or Atlassian.
RELATED Other topics · full topics ranking →
#claude-code
122#ai-agents
73#claude
73#mcp
71#llm
67#python
56#developer-tools
49#ai
45#anthropic
42Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology