The Agent Skills Directory

[COMMAND_EXECUTION]: The skill contains numerous scripts designed to execute high-privilege system commands. For example, references/incident-response.md includes collect-evidence.sh and game-day scripts that use kubectl, tcpdump, and slack-cli. references/platform-engineering.md provides create-service.sh which executes gh and git commands to modify repositories.
[PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) due to its operational model.
Ingestion points: references/incident-response.md contains the collect-evidence.sh script which ingests pod logs, cluster state (YAML), and database activity. references/platform-engineering.md includes a FastAPI-based Platform API that processes ServiceRequest objects from external users.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when processing ingested logs or metadata.
Capability inventory: The skill possesses extensive capabilities across all reference files, including subprocess execution of kubectl, terraform, docker, and gh commands, as well as the ability to patch Kubernetes deployments via Python scripts (IncidentRemediator).
Sanitization: The provided automation templates do not include explicit sanitization or validation logic for external content before it is processed or used in decision-making workflows.

devops-engineer