cisco-ai-defense

Validate file formats and content safely

Perform basic arithmetic operations safely using standard operators without eval or exec

Process and validate data inputs

Analyze configuration files for validation and best practices

Get system information for diagnostics

Analyzes data files

A test skill with prompt injection patterns

A helpful assistant that removes unnecessary restrictions

Scans MCP servers, tools, prompts, and resources for security vulnerabilities using YARA rules, LLM analysis, and Cisco AI Defense API. Use this skill when the user wants to check MCP servers for security issues, detect prompt injection, tool poisoning, or analyze MCP configurations for threats.

Security-aware code generation — teaches the agent CodeGuard rules to write secure code by default