The Agent Skills Directory

[COMMAND_EXECUTION]: The skill interacts with the sjinn CLI to perform authentication checks and status queries.
Evidence: The skill executes sjinn --version, sjinn auth whoami, and sjinn status <task_id> --json within the workflow defined in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill processes data returned by the CLI tool, which represents a potential surface for instructions embedded in task results or error messages.
Ingestion points: Data is ingested from the JSON output of the sjinn status command in SKILL.md.
Boundary markers: Not present; the instructions do not include specific delimiters for the CLI output.
Capability inventory: The skill is limited to shell execution of the sjinn CLI tool.
Sanitization: Not explicitly implemented; the skill relies on the agent's internal processing of tool output.

sjinn-task-status