The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the @pachca/cli package from the npm registry. This is a legitimate vendor resource provided by Pachca for interacting with their API.
[COMMAND_EXECUTION]: The skill carries out its functions by executing shell commands through the Pachca CLI. This includes operations like sending messages, searching for chats, and uploading files.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it takes user-provided text and interpolates it into shell command arguments.
Ingestion points: User-supplied text for message content (--content) and search queries (--query) in SKILL.md workflows.
Boundary markers: Commands use double quotes to wrap interpolated user data.
Capability inventory: Shell execution capabilities for messaging, file management, and search via the @pachca/cli tool.
Sanitization: The instructions do not specify explicit sanitization or escaping of the user-provided content before execution.

pachca-messages