# A Map of the Main Risk Families — LLM Application Security

Source: https://www.geekswithgeeks.com/en/llm-security/t-map

> Preview the risks this course covers and how they connect.

## Ten-ish risks, four themes

The usual risk lists group into four themes. **Manipulation**: prompt injection (direct and indirect), jailbreaks, system-prompt leakage. **Unsafe consequences**: insecure handling of model output (XSS, SQL injection, command injection, path traversal, SSRF), excessive agency, over-reliance on wrong answers. **Data and knowledge**: sensitive-information disclosure, training-data or retrieval poisoning, weaknesses in embeddings and vector stores, RAG access-control failures. **Platform and resources**: supply chain (models, packages, plugins, serialised files), unbounded consumption (denial of service, denial of wallet), and monitoring gaps. The fixes come from the same short list of principles: **least privilege, validate everything crossing a boundary, keep humans in the loop for risky actions, separate data from instructions where you can, limit resources, log and test**. The rest of the course turns these into concrete practice.

## Risk families and main controls

A cheat sheet for the sections ahead.

```text
Theme              Risk                                   Main controls
Manipulation       prompt injection, jailbreak, prompt leak   data/instruction separation, least privilege, approvals, never keep secrets in prompts
Unsafe consequence insecure output handling                   escape / parameterise / allow-list / validate before use
                   excessive agency                           narrow tools, per-user auth, human approval, audit
Data & knowledge   sensitive disclosure, RAG leaks, poisoning access control in retrieval, redaction, provenance, minimal retention
Platform           supply chain, unbounded consumption         pin & verify models/packages, safe formats, rate and spend limits, monitoring
```

## Use a maintained checklist

Start from the OWASP Top 10 for LLM Applications and adapt it to your system; the list changes over time.

**Quiz:** Which principle underlies most of the fixes?

- [ ] Using longer prompts
- [x] Least privilege and validating everything that crosses a boundary
- [ ] Hiding the model name
- [ ] Using more GPUs

*Answer:* Least privilege and validating everything that crosses a boundary. Classic security principles still apply and do most of the work.