ToolAI Ethics & Safetyv0.9

Vigil

by deadbits · open-source · Last verified 2026-03-17

Open-source prompt injection scanner for detecting and preventing attacks on LLM applications. Provides multiple detection methods including similarity matching, canary tokens, and heuristic analysis.

https://github.com/deadbits/vigil-llm ↗

D—Poor

Adoption: DQuality: B+Freshness: B+Citations: DEngagement: F

Specifications

License: MIT
Pricing: open-source
Capabilities: prompt-injection-scanning, canary-tokens, similarity-detection, heuristic-analysis
Integrations
Use Cases: prompt-injection-detection, input-scanning, security-auditing
API Available: Yes
SDK Languages: python
Deployment: self-hosted
Rate Limits: N/A (open-source)
Data Privacy: Self-hosted, user-managed; runs locally
Tags: prompt-injection, scanner, open-source, security
Added: 2026-03-17
Completeness: 100%

Index Score

31.45

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service