Fill in a couple of links

Summary: As titled, just a couple of links that are only available post-launch

Reviewed By: csahana95

Differential Revision: D60135624

fbshipit-source-id: 42a265c8fc73d272ce4b05908f0ad8aa3af4f440

CybersecurityBenchmarks/website/docs/prompt_guard/overview.md

@@ -44,10 +44,10 @@ upholding the principles of openness. Our mission is to empower individuals, and
 industry through this opportunity, while fostering an environment of discovery
 and ethical AI advancements.
 
-The same license as Llama 3 applies: see the [LICENSE](../LICENSE.md) file, as well
-as our accompanying Acceptable Use Policy.
+The same license as Llama 3 applies: see the [LICENSE](../LICENSE.md) file, as
+well as our accompanying Acceptable Use Policy.
 
 # References
 
-- Llama 3 Paper
-- CyberSecEval 3
+- [Llama 3 Paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/)
+- [CyberSecEval 3](https://ai.meta.com/research/publications/cyberseceval-3-advancing-the-evaluation-of-cybersecurity-risks-and-capabilities-in-large-language-models/)

Prompt-Guard/README.md

@@ -32,7 +32,7 @@ and
 Please report any software bug, or other problems with the models through one of
 the following means:
 
-- Reporting issues with the Llama Guard model:
+- Reporting issues with the Prompt Guard model:
   [github.com/meta-llama/PurpleLlama](https://github.com/meta-llama/PurpleLlama)
 - Reporting issues with Llama in general:
   [github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)
@@ -51,5 +51,5 @@ as our accompanying [Acceptable Use Policy](USE_POLICY.md).
 
 # References
 
-- [Llama 3 Paper](TBD)
-- [CyberSecEval 3](TBD)
+- [Llama 3 Paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/)
+- [CyberSecEval 3](https://ai.meta.com/research/publications/cyberseceval-3-advancing-the-evaluation-of-cybersecurity-risks-and-capabilities-in-large-language-models/)