The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the ailang CLI and the GitHub CLI (gh) to perform message management tasks, such as listing, reading, and acknowledging messages.
[DATA_EXFILTRATION]: Messages can be synchronized to GitHub issues using the --github flag, which moves local message data to an external repository for bug reporting and feature tracking.
[PROMPT_INJECTION]: The skill ingests and summarizes messages from external autonomous agents and GitHub issues. This ingestion of untrusted external content represents a surface for indirect prompt injection where malicious instructions in a message could attempt to influence the agent's behavior.
Ingestion points: ailang messages list and ailang messages read (SKILL.md)
Boundary markers: None explicitly defined in the provided commands to isolate message content.
Capability inventory: Shell execution via ailang and file system access via cat and ls (SKILL.md)
Sanitization: No specific sanitization or filtering of message payloads is described.
[EXTERNAL_DOWNLOADS]: The installation procedure involves downloading the skill documentation from a third-party GitHub repository (majiayu000/claude-skill-registry).

Agent Inbox