majiayu000 LLM Application Security
Harden chatbots and AI features embedded in web and mobile products.
Baseline Security Checklist
- Validate and classify all user-provided context.
- Separate system prompts from user content strictly.
- Add moderation for toxic, harmful, and policy-violating outputs.
- Enforce tenant boundaries in retrieval and memory layers.
- Rate-limit high-cost endpoints.
Secure RAG Pattern
- Ingest content with malware and secret scanning.
- Tag documents by tenant and access policy.
- Filter retrieval candidates by user authorization.
- Add provenance metadata in final responses.
Related Skills
- ai-agent-security - Agent-specific controls
- sast-scanning - Secure coding checks