The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes dynamic context injection (the !command syntax) in SKILL.md to execute a shell command chain at load time to check for the presence and status of the opencli tool.
[EXTERNAL_DOWNLOADS]: The skill directs the user to install the @jackwener/opencli package globally via npm. This package originates from an unverified third-party account rather than a known or trusted organization.
[PROMPT_INJECTION]: The skill is designed to ingest and process data from Discord, which constitutes untrusted external content.
Ingestion points: Discord data enters the agent context via the output of opencli discord-app read and opencli discord-app search commands.
Boundary markers: The prompt instructions lack explicit delimiters or instructions to treat the ingested Discord content as untrusted data.
Capability inventory: The skill environment allows for shell command execution and package installation.
Sanitization: There is no mechanism described for sanitizing or filtering the content retrieved from Discord before it is used to inform agent decisions or outputs.

discord-reader