The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the gh (GitHub) and acli (Atlassian) CLI tools to perform operations such as listing issues, viewing content, updating labels, and transitioning statuses.
[EXTERNAL_DOWNLOADS]: References the Atlassian CLI (acli) through an official documentation and resource link on the developer.atlassian.com domain.
[PROMPT_INJECTION]: The skill's primary function involves processing untrusted data from GitHub and Jira issue trackers, creating an indirect prompt injection surface.
Ingestion points: Issue titles, bodies, and comments are retrieved via the tracker CLI tools as documented in tracker-github.md and tracker-jira.md.
Boundary markers: The skill instructions do not explicitly mandate delimiters or safety headers to separate untrusted issue content from the agent's instructions, though standard heredoc syntax is used in CLI examples.
Capability inventory: The agent possesses capabilities to modify tracker state (labels, status), post comments, and perform local file writes to the .out-of-scope/ directory.
Sanitization: There is no explicit requirement for sanitizing or validating the text retrieved from external issue trackers before processing.

triage