ci: auto-fix validation errors - add missing badge for LlamaFirewall

Author: alvinreal

README.md

@@ -747,7 +747,7 @@
 - **[Garak (NVIDIA)](https://github.com/NVIDIA/garak)** ![GitHub stars](https://img.shields.io/github/stars/NVIDIA/garak?style=social) - The LLM vulnerability scanner. Probes models for hallucinations, data leakage, prompt injection, misinformation, toxicity, and jailbreaks. Extensive plugin-based architecture with 100+ vulnerability probes. Apache 2.0 licensed.
 - **[Promptfoo](https://github.com/promptfoo/promptfoo)** ![GitHub stars](https://img.shields.io/github/stars/promptfoo/promptfoo?style=social) - Open-source LLM evaluation and red teaming framework. Test prompts, agents, and RAGs with automated security vulnerability scanning, side-by-side model comparison, and CI/CD integration. Now part of OpenAI. MIT licensed.
 - **[DeepTeam (Confident AI)](https://github.com/confident-ai/deepteam)** ![GitHub stars](https://img.shields.io/github/stars/confident-ai/deepteam?style=social) - Red teaming framework for LLM systems with 50+ vulnerabilities, 20+ adversarial attacks, and production-ready guardrails. Includes OWASP, NIST, and MITRE ATLAS framework mappings. Apache 2.0 licensed.
-- **[LlamaFirewall](https://github.com/meta-llama/PurpleLlama/tree/main/LlamaFirewall)** - Open-source guardrail system specifically designed for securing AI agents. Features PromptGuard 2 for jailbreak detection, Agent Alignment Checks for chain-of-thought auditing, and CodeShield for insecure code detection. Part of PurpleLlama. BSD-3-Clause licensed.
+- **[LlamaFirewall](https://github.com/meta-llama/PurpleLlama/tree/main/LlamaFirewall)** ![GitHub stars](https://img.shields.io/github/stars/meta-llama/PurpleLlama?style=social) - Open-source guardrail system specifically designed for securing AI agents. Features PromptGuard 2 for jailbreak detection, Agent Alignment Checks for chain-of-thought auditing, and CodeShield for insecure code detection. Part of PurpleLlama. BSD-3-Clause licensed.
 
 ---