The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs the agent to run npx -y xno-skills, which downloads and executes code from a remote registry at runtime. The package xno-skills is not associated with a trusted organization or the skill author's verified namespace, posing a risk of executing malicious code if the package is compromised or malicious.
[COMMAND_EXECUTION]: The skill uses npx to execute CLI commands in the host environment, providing a direct path to the system shell.
[EXTERNAL_DOWNLOADS]: Runtime execution triggers the download of the xno-skills package from the public NPM registry.
[PROMPT_INJECTION]: The skill processes untrusted user data (Nano address and amount) by interpolating it into a shell command template, creating a surface for indirect injection.
Ingestion points: Wallet address and amount provided by the user in SKILL.md.
Boundary markers: Absent; no delimiters are used to isolate user input from the command string.
Capability inventory: Direct shell command execution via npx as documented in SKILL.md.
Sanitization: No explicit validation, escaping, or filtering of the user-provided address is defined before it is passed to the command line.

generate-qr