The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the treehouse CLI tool to perform worktree operations such as get, return, and status. This is the core functionality of the skill and is used for project task isolation.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes output from the treehouse status and treehouse return commands. If an environment contains malicious filenames or if the tool output is manipulated, it could influence the agent's behavior.
Ingestion points: Tool output from treehouse status and treehouse return (referenced in SKILL.md).
Boundary markers: No explicit boundary markers or instructions to ignore embedded content are provided.
Capability inventory: The agent can execute shell commands via the treehouse tool.
Sanitization: There is no evidence of sanitization or validation of the tool's output before the agent acts on it.
[EXTERNAL_DOWNLOADS]: The skill documentation includes a link to the Treehouse source code hosted on GitHub (github.com/kunchenguid/treehouse) for troubleshooting and reference. GitHub is a well-known service, and this reference is for documentation purposes rather than runtime script execution.

treehouse