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.
In the LLM eval & observability space, cisco-ai-skill-scanner takes a focused approach. It detects security vulnerabilities such as prompt injection and malicious code in AI Agent Skills packages. It is built as an open-source project for ai security engineers. cisco-ai-skill-scanner is open source under the Apache-2.0 license. It runs on the web and the command line.
Behind cisco-ai-skill-scanner is Cisco AI Defense, and it first shipped in 2026. Development happens publicly on GitHub with 2.2k stars and 32 commits in the last 90 days. Key capabilities include prompt injection detection, static analysis, and threat detection. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do