The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to use npx ai-nginx, which downloads and executes the ai-nginx package from the npm registry at runtime. This package originates from an external source (LXGIC Studios/ThinkfleetAI) that is not included in the pre-defined list of trusted organizations or well-known services.
[COMMAND_EXECUTION]: The primary functionality relies on executing shell commands with arguments derived from natural language descriptions (e.g., npx ai-nginx "..."). If user-provided text contains shell metacharacters such as semicolons, pipes, or backticks, it could lead to arbitrary command execution on the host system.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted "plain English" descriptions into command arguments.
Ingestion points: User-provided descriptions are passed to the ai-nginx CLI tool via shell arguments.
Boundary markers: No explicit boundary markers or sanitization logic is present in the skill instructions to prevent the agent from including malicious shell commands in the execution string.
Capability inventory: The skill possesses the capability to execute subprocesses through the shell via npx.
Sanitization: There is no evidence of input validation or escaping for the shell commands.

nginx-gen