The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes the gh CLI to interact with GitHub repositories. Specific commands include gh label create for triage organization, gh issue create for ticket generation, and gh api for managing issue sub-tasks and native dependencies. These actions are transparently described and aligned with the skill's primary purpose.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process external content such as specifications or existing GitHub issues to generate work items. This creates a surface where malicious instructions embedded in those external sources could attempt to influence the agent's output.
Ingestion points: The agent is instructed in SKILL.md to fetch and read the full body and comments of external references (issue numbers/URLs or spec paths) provided by the user.
Boundary markers: There are no explicit instructions or delimiters defined to isolate the untrusted external content from the agent's core instructions.
Capability inventory: The skill utilizes gh CLI commands to create and modify repository content such as issues and labels.
Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the data retrieved from external references, though the skill includes a mandatory user review step before execution.

to-tickets