Back to browse
GitHub Repository

Open-Source Prompt Injection Scanner for AI agents. 225 detection patterns across 17 categories, 15 languages. REST API, EU AI Act compliance mapping, <10ms latency.

11 starsPython

ClawGuard – Detect 42 prompt injection patterns in <10ms

by joergmichno·Mar 9, 2026·2 points·3 comments

AI Analysis

●●SolidNiche GemShip It

42 prompt injection patterns detected in under 10ms with zero dependencies.

Strengths
  • Pure Python standard library means no dependency conflicts in production deployments.
  • Bilingual detection covers both English and German attack patterns effectively.
  • Complete ecosystem with Shield API, Python SDK, GitHub Action, and MCP Server.
Weaknesses
  • Zero stars on GitHub suggests very early adoption and unproven production use.
  • Pattern-based detection may miss novel injection techniques not in the 42 rules.
Category
Target Audience

AI developers building autonomous agents

Similar To

Lakera Guard · Rebuff · PromptArmor

Similar Projects