The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads and executes the @pachca/cli package from the NPM registry using the npx utility.
[COMMAND_EXECUTION]: Shell commands are used to invoke the pachca CLI tool for searching messages, chats, and users, as well as managing authentication status.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content retrieved from external Pachca search results, which could contain embedded instructions intended to influence the agent.
Ingestion points: Data returned from pachca search list-messages, pachca search list-chats, and pachca search list-users commands.
Boundary markers: None present in the instructions to delimit external content or warn the agent about embedded instructions.
Capability inventory: Ability to execute shell commands via Bash(npx:*) and Bash(pachca:*) tools.
Sanitization: No explicit sanitization or validation of the search result content is described.

pachca-search