tirith
Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated payloads, data exfiltration, and malicious AI skills/configs before they execute.
Conjuntos de instrucciones (skills) que enseñan a la IA una forma de trabajar, de repos de GitHub con 200+ estrellas y un SKILL.md real · no son MCP servers
En qué se diferencia un Skill de MCP →
Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated payloads, data exfiltration, and malicious AI skills/configs before they execute.
Trail of Bits skills for security research, vulnerability detection, and audit workflows
Easily find and fix security issues in your applications leveraging Snyk platform capabilities.
Search security detections across Sigma, Splunk, Elastic, KQL, Sublime, CQL and Jamf with ATT&CK.
Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
Connects AI agents with CrowdStrike Falcon for security analysis and automation.
Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants.