The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses cat to read the Jira configuration file located at ~/.config/.jira/.config.yml. This file is a sensitive path that often contains Jira authentication tokens or session information.
[PROMPT_INJECTION]: The skill processes summaries, descriptions, and comments from Jira tickets, which are untrusted external inputs. This introduces a risk of indirect prompt injection where malicious instructions embedded in a ticket could influence the agent's analysis or subsequent actions.
Ingestion points: Data is fetched from Jira using jira issue list in Phases 2 and 3 of the workflow.
Boundary markers: None. The skill lacks delimiters (such as XML tags) or instructions to the agent to ignore embedded commands within the ticket data.
Capability inventory: The skill has access to Bash (git, jira, cat) and TodoWrite tools, which allows it to modify repositories and write task files.
Sanitization: No evidence of sanitization or escaping of the retrieved Jira ticket content is present before it is analyzed by sub-agents.

jira-todo