The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill uses variables such as branch names and effort labels which are passed as arguments to the treehouse command-line utility, creating a surface for indirect prompt injection.
Ingestion points: External data enters the agent context via the <effort> label in the --lease-holder flag and the <branch> name in the -b flag, as described in SKILL.md.
Boundary markers: The instructions do not define delimiters or provide warnings to the agent to ignore instructions that might be embedded within these user-supplied strings.
Capability inventory: The skill possesses the capability to terminate system processes (via treehouse return and treehouse destroy --include-in-use) and perform recursive file deletion (via treehouse destroy) as documented in the Gotchas section.
Sanitization: There are no instructions for validating, escaping, or sanitizing the input strings before they are incorporated into shell commands.
[EXTERNAL_DOWNLOADS]: The skill references and relies on a specific version of a tool hosted on a third-party GitHub repository (github.com/kunchenguid/treehouse). This repository is not associated with the skill author nor is it part of a recognized trusted organization.
[COMMAND_EXECUTION]: The skill's primary function is to guide the agent in executing shell commands using the treehouse tool to manage system resources, including processes and file system paths.

treehouse