The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves pull request and issue titles from GitHub (via the gh CLI) and branch names from Git to populate Paseo workspace titles.
Ingestion points: Data enters the context through gh issue view --json title and git worktree list in SKILL.md.
Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to disregard instructions potentially embedded within these external strings.
Capability inventory: The skill uses the Bash tool to perform sensitive operations like paseo workspace rename and git worktree remove based on retrieved data.
Sanitization: There is no evidence of sanitization or filtering applied to external strings before they are used in commands.
[COMMAND_EXECUTION]: The skill relies on the Bash tool to execute a wide range of commands including git, gh, and paseo. While these are within the primary scope of managing worktrees, they provide a powerful interface that could be exploited if the agent context is compromised through indirect injection.

paseokit