The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires standard Node.js libraries node-fetch and https-proxy-agent as defined in package.json for handling network requests and proxy support.
[DATA_EXFILTRATION]: The skill reads the DISCORD_BOT_TOKEN and DISCORD_USER_ID environment variables. These credentials are transmitted to discord.com, which is a well-known service, for the intended purpose of authenticating the bot and identifying the recipient user.
[COMMAND_EXECUTION]: The SKILL.md instructions direct the agent to execute a diagnostic script node check.js to verify the environment configuration and test connectivity to the Discord API.
[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by accepting arbitrary text from the agent and transmitting it to the user's Discord client.
Ingestion points: send.js receives the notification message via command-line arguments, which are populated by the agent based on its current context or task results.
Boundary markers: The skill does not employ delimiters or specific instructions to the agent to ignore or escape potentially malicious instructions embedded in the data it processes.
Capability inventory: The skill has the capability to perform authenticated network requests to the Discord API to send messages.
Sanitization: No sanitization, validation, or filtering is performed on the message content before it is sent to the external Discord service.

discord-notify