The Agent Skills Directory

[COMMAND_EXECUTION]: The skill defines a wide range of shell commands for the acli tool, facilitating project management, work item automation, and administrative user operations. These include high-privilege operations such as project deletion and user account deactivation.\n- [PROMPT_INJECTION]: The skill's primary function involves retrieving and processing data from Jira Cloud (summaries, descriptions, and comments), creating a vulnerability surface for indirect prompt injection. Malicious instructions embedded in Jira work items could influence agent behavior during processing.\n
Ingestion points: Data enters the agent's context through subcommands such as acli jira workitem view and acli jira workitem search (documented in SKILL.md and workitem.md).\n
Boundary markers: The instructions do not specify any delimiters or safety warnings for the agent to distinguish between data and instructions when reading Jira content.\n
Capability inventory: The skill provides access to destructive capabilities including acli jira project delete, acli jira workitem delete, and acli admin user delete across all reference files.\n
Sanitization: There are no documented steps for validating or sanitizing the content retrieved from Atlassian before it is processed by the agent.

atlassian-cli