Alpha-Park/genpark-agent-prompt-guard-injection-sanitizer-skill
Strict heuristic and regex-based prompt injection and untrusted input guard detecting jailbreak markers, hidden instruction escapes, and indirect injection payloads
GitHub repository with 8 stars and 0 forks.
Language: Python
Topics: agentic-workflow, ai-agent, ai-security, autonomous-agents, developer-tools, enterprise-ai, mcp, model-context-protocol, multi-agent-systems, python-standard-library