The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands via the jira CLI to interact with Jira project data. It includes shell loops for bulk operations and uses temporary files in /tmp to handle multi-line issue descriptions.\n- [PROMPT_INJECTION]: The skill has an attack surface for Indirect Prompt Injection because it reads and processes untrusted content from external Jira tickets.\n
Ingestion points: Commands defined in references/cli-reference.md (e.g., jira issue view, jira issue list) retrieve ticket summaries, descriptions, and comments from a remote server.\n
Boundary markers: The skill does not use delimiters or instructions to ignore potential commands embedded within the retrieved Jira data.\n
Capability inventory: The documentation in SKILL.md and references/cli-reference.md demonstrates capabilities to modify the Jira environment, including creating, editing, and transitioning issues.\n
Sanitization: No evidence of sanitization or validation of the fetched Jira content is provided before it is processed by the agent.

managing-jira