The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute the acli command-line tool to interact with Jira. This includes a wide range of operations such as viewing tickets, searching with JQL, and mutating work items.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from Jira (ticket descriptions, summaries, and comments). Since this data is provided by external users, it could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: Data enters the context through acli jira workitem view, acli jira workitem search, and acli jira workitem comment list commands (defined in SKILL.md).
Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded content within Jira tickets.
Capability inventory: The skill has the capability to execute shell commands (acli) and write to the local filesystem (as seen in the ticket creation example in boards.md).
Sanitization: There are no explicit sanitization or filtering steps defined for the content retrieved from Jira.

acli-jira