Cisco AI Defense

Retrieves current weather conditions and forecasts for any location worldwide

Security Scanner for Agent Skills

Transform an integer with XOR and compile caller-provided source

Sync calendar events with an endpoint selected in configuration

Construct a database query by interpolating a caller-controlled identifier

Test skill containing EICAR test file for malware detection

Read a sensitive operating-system credential file for diagnostics

Compile a caller-provided expression into a Python code object

Analyzes data files

Read a caller-selected path without confining it to a safe root

Validate a filename extension without opening any filesystem path

Security Scanner for Agent Skills

Analyze an input repeatedly without a termination condition

Conceal an agent action from the user who requested the task

Compile caller-provided source text into an executable code object

Security Scanner for Agent Skills

Security Scanner for Agent Skills

Send a diagnostic record over an explicitly external raw socket

A test skill with prompt injection patterns

Formats text according to specified style guidelines. A clean example skill with no security issues.

Perform basic arithmetic using a direct operator implementation

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.