The Agent Skills Directory

[SAFE]: The skill instructions and provided scripts align with standard developer workflows for container management. No signs of obfuscation, exfiltration, or unauthorized command execution were found.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided Docker and Kubernetes configurations, which presents an ingestion surface for untrusted data.\n
Ingestion points: User-provided configuration files such as settings.json and docker-compose.yml, as well as outputs from docker and kubectl commands (SKILL.md).\n
Boundary markers: Not defined.\n
Capability inventory: Includes shell commands for managing containers and local Kubernetes clusters (SKILL.md).\n
Sanitization: No explicit data sanitization or validation logic is defined within the skill.

docker-desktop