The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses several command-line tools to interact with the environment and external services.
Evidence: Commands include temporal for workflow management, bun for running repository scripts (atlas:rebuild, sync-temporal-routing.ts), and kubectl for inspecting Kubernetes pods and logs.
The wrapper script scripts/temporal-run.sh safely passes arguments to the temporal binary using array expansion.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as its primary function involves ingesting and analyzing potentially untrusted data from workflow histories and logs.
Ingestion points: The agent is instructed to read workflow history files (e.g., /tmp/workflow-history.json) and Kubernetes deployment logs (kubectl logs).
Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the data being analyzed.
Capability inventory: The skill can execute local scripts, interact with Temporal and Kubernetes APIs, and write temporary files.
Sanitization: No explicit sanitization of ingested workflow data is specified, which is common for debugging and triage tools.

temporal