The Agent Skills Directory

[COMMAND_EXECUTION]: The skill resolves and executes various CLI commands (such as orca, orca-dev, orca-ide, or the path specified in the ORCA_CLI_COMMAND environment variable) to interact with Jira systems.
[PRIVILEGE_ESCALATION]: The instructions explicitly direct the agent to re-run commands with escalated permissions if it encounters a runtime_access_denied error, which is an instruction to bypass sandbox constraints.
[DYNAMIC_EXECUTION]: The skill uses the ORCA skills get orca-jira command to dynamically fetch and load a version-matched guide at runtime, introducing instructions that are not present in the static skill file.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from Jira issue fields, comments, and labels, which are identified as untrusted sources.
Ingestion points: Jira issue data, including comments and labels, are read through the CLI into the agent's context.
Boundary markers: While the description warns to treat fields as untrusted, there are no structural boundary markers or specific instructions for the agent to use delimiters when processing this data.
Capability inventory: The skill possesses command execution capabilities through the Orca CLI tools.
Sanitization: No specific sanitization, filtering, or escaping mechanisms for the ingested Jira data are described.

orca-jira