SkillWard is a web-based dashboard that automates security analysis of skill packages through static analysis, LLM-based evaluation, and sandbox execution. Below are 6 llm eval & observability apps with similar functionality to Skills Scanner Pipeline, matched by what each product actually does — not ranked or scored. Explore each to find the closest fit for your use case.
SkillScan is an open-source CLI tool for static security analysis of AI agent skill files. It detects malicious patterns, prompt injection, data exfiltration, and container escape techniques, supporting secure development and deployment workflows.
Security Skill is an open-source CLI tool that integrates advanced security modules into AI coding assistants such as Cursor, Claude, and Copilot. It helps developers detect and fix vulnerabilities automatically in their codebases.
cisco-ai-skill-scanner is an open-source CLI tool for scanning Agent Skills packages to detect prompt injection, data exfiltration, and malicious code. It is designed for AI security engineers and developers working with LLM agents and skills.
skill-auditor is an open-source command-line tool that scans AI Agent skills for security issues before installation. It acts as an install gate, helping developers and maintainers ensure that only safe and validated skills are added to their AI agents. Ideal for those building or managing AI agent frameworks.
skillsafe is an open-source CLI client for managing AI coding tool skills. It allows developers to scan, save, share, install, and verify skills securely via a command-line interface. Ideal for developers seeking to manage AI skills across tools with security and transparency.
agent-skill-scanner is an open-source CLI tool that scans agent skill files for security vulnerabilities, including prompt injection, capability escalation, and data exfiltration. It applies 22 security rules to help AI developers and security researchers identify and mitigate risks in LLM agent skills. The tool is MIT licensed and suitable for anyone building or auditing AI agent systems.
