diff options
| author | Addy Osmani <addyosmani@gmail.com> | 2026-06-07 15:26:33 -0700 |
|---|---|---|
| committer | Addy Osmani <addyosmani@gmail.com> | 2026-06-07 15:26:33 -0700 |
| commit | cad41cb506dfe56fa45e94f70a74cc6efe0cbf8a (patch) | |
| tree | c57c0233c7ba0fd3a3414d5bc33eae8940caba1a | |
| parent | d1983929db658cf86905c75bbf1306d2fa39dbb1 (diff) | |
docs(security): complete the OWASP LLM Top 10 quick-reference tablesecurity
Per federicobartoli's note on #219: the table was headed "Top 10" but
listed only 8. Add the two missing entries (LLM04 Data and Model Poisoning,
LLM09 Misinformation) so the heading matches the contents.
| -rw-r--r-- | references/security-checklist.md | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/references/security-checklist.md b/references/security-checklist.md index 1b7eea0..553c388 100644 --- a/references/security-checklist.md +++ b/references/security-checklist.md @@ -170,8 +170,10 @@ For apps with LLM features. See the [OWASP GenAI Security Project](https://genai | LLM01 | Prompt Injection | Don't trust the system prompt as a boundary; enforce permissions in code | | LLM02 | Sensitive Information Disclosure | Keep secrets/PII out of prompts; filter outputs | | LLM03 | Supply Chain | Vet models, datasets, and plugins like any dependency | +| LLM04 | Data and Model Poisoning | Use trusted model sources, verify integrity; vet fine-tuning and RAG data | | LLM05 | Improper Output Handling | Treat model output as untrusted; validate, parameterize, encode | | LLM06 | Excessive Agency | Scope tool permissions; confirm destructive actions | | LLM07 | System Prompt Leakage | Assume the system prompt can leak; put no secrets in it | | LLM08 | Vector and Embedding Weaknesses | Partition RAG embeddings per tenant; validate documents before indexing | +| LLM09 | Misinformation | Ground answers with citations; validate critical claims; keep a human in the loop | | LLM10 | Unbounded Consumption | Cap tokens, request rate, and loop/recursion depth | |
