Add project: Sentinel AI

[MaxwellCalkin]

Add project: Sentinel AI

• GitHub: https://github.com/MaxwellCalkin/sentinel-ai
• Category: Adversarial Robustness
• License: Apache 2.0

Description

Sentinel AI is a real-time safety guardrails library for LLM applications. It provides 8 scanners for detecting prompt injection, PII leakage, harmful content, hallucination, toxicity, blocked terms, tool-use validation, and structured output validation.

Key features

• 8 built-in scanners covering major LLM safety concerns
• Multilingual injection detection across 12 languages + cross-lingual attacks
• MCP Safety Proxy for transparent safety layer on any MCP server
• Sub-millisecond latency (~0.05ms average scan time)
• 530 benchmark cases, 100% accuracy (0 FP, 0 FN)
• Zero heavy dependencies in core (only regex)

Changes

Added Sentinel AI to projects.yaml under the adversarial category, as it focuses on defending LLM applications against adversarial attacks (prompt injections, jailbreaks, etc.).

---

Summary by cubic

Adds MaxwellCalkin/sentinel-ai to projects.yaml under the adversarial category. This lists a real-time LLM safety guardrails library with 8 scanners (prompt injection, PII, harmful content, hallucination, toxicity, and more).

^{Written for commit f48a0e9. Summary will update on new commits.}

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, you can upgrade your account or add credits to your account and enable them for code reviews in your settings.

[cubic-dev-ai]

No issues found across 1 file