The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent and user to install the wtp utility from an external third-party repository (github.com/satococoa/wtp) using Homebrew or Go installation commands.- [COMMAND_EXECUTION]: The skill utilizes the wtp exec command to run arbitrary commands within worktrees and suggests using eval for shell initialization (wtp shell-init). It also manages repository-defined execution hooks through the .wtp.yml configuration file.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via malicious repository configuration files. * Ingestion points: The agent is instructed to read and act upon .wtp.yml and lockfiles found in the repository root (e.g., in SKILL.md Agent workflow section). * Boundary markers: No boundary markers or 'ignore' instructions are provided to the agent when processing these external files. * Capability inventory: The skill has the capability to execute shell commands via wtp exec and trigger automated hooks via wtp add. * Sanitization: No sanitization or validation of the repository-provided configuration or hooks is performed before execution.

jb-worktree