The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Bash(jira *) to fetch issue lists, current user info, and ticket details from the Jira CLI. It also uses Bash(git *) to gather local development context like branch names and recent commits.
[COMMAND_EXECUTION]: Reads the local configuration file at ~/.config/.jira/.config.yml to automatically detect the active project key. This is standard behavior for CLI-integrated tools.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted data from Jira ticket fields (summaries, descriptions, comments) and feeds them into prompts for sub-agents.
Ingestion points: Jira API data retrieved via jira issue list in SKILL.md (Phase 2).
Boundary markers: Absent; ticket data is passed directly to analysis prompts in Phase 3.
Capability inventory: The skill can execute shell commands (Bash), read local files, and write to todo lists.
Sanitization: None; external content is processed as raw text for analysis.

jira-todo