The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and run the official Pachca CLI package (@pachca/cli) from the NPM registry using npx or npm. This is a standard integration method for the vendor's services.
[COMMAND_EXECUTION]: The skill relies on shell command execution via the Bash tool to run CLI commands for chat management, as explicitly permitted in the skill's frontmatter configuration.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from the Pachca API.
Ingestion points: Chat metadata (names, activity status) and member lists are ingested through commands like pachca chats list and pachca members list (SKILL.md).
Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions that might be embedded in the retrieved data.
Capability inventory: The agent possesses the capability to execute arbitrary shell commands via the Bash tool (allowed for npx, pachca, etc.).
Sanitization: There is no evidence of sanitization or validation performed on the API data before it is presented to the agent's context.

pachca-chats