The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes shell commands for verifying API health using curl and provides deployment scripts for Docker, Terraform, and Kubernetes. These commands are typical for infrastructure-as-code and service integration tasks.
[EXTERNAL_DOWNLOADS]: The skill interacts with api.twinmind.com for health checks and references standard container images from public registries (e.g., node:20-alpine, redis:7-alpine). These external resources are consistent with the skill's primary purpose of deploying TwinMind integrations.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a standard attack surface for indirect prompt injection, as it includes tools capable of reading project files and executing shell commands based on the context of the deployment.
Ingestion points: Project configuration and source files accessed via the Read tool.
Boundary markers: None explicitly defined in the provided deployment templates to distinguish between instructions and data.
Capability inventory: Full shell execution via Bash and file system modification via Write and Edit tools.
Sanitization: No input validation or sanitization is implemented in the provided CI/CD and infrastructure templates.

twinmind-deploy-integration