The Agent Skills Directory

[COMMAND_EXECUTION]: The skill triggers its primary functionality by executing a Node.js script (send.js) via a shell command as documented in SKILL.md.
[EXTERNAL_DOWNLOADS]: The skill's package.json specifies dependencies on well-known libraries node-fetch and https-proxy-agent for managing HTTP requests and proxy configurations.
[DATA_EXFILTRATION]: User-provided message content is transmitted to the official Discord API (https://discord.com/api/v10/). This network operation is the intended purpose of the skill.
[PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection by placing untrusted user input into a shell command template in SKILL.md.
Ingestion points: The MESSAGE argument in the CLI execution command within SKILL.md.
Boundary markers: Absent; input is enclosed in double quotes.
Capability inventory: Execution of local scripts and network transmission to external APIs via send.js.
Sanitization: None provided within the skill's scripts; relies on the agent platform to handle shell escaping.
[SAFE]: The skill follows security best practices for secret management by requiring the DISCORD_BOT_TOKEN to be provided via environment variables rather than hardcoding credentials.

discord-notify