The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the argocd CLI to manage Kubernetes cluster state. It includes commands for application synchronization, creation, and rollback, which are necessary for the skill's primary function of infrastructure management.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to ingest and process external data from Kubernetes logs and Git repository manifests.- Ingestion points: argocd app logs, argocd app manifests, and argocd app get in SKILL.md.- Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between tool output and control instructions.- Capability inventory: The agent has the ability to execute the argocd CLI with permissions to modify, delete, and create cluster resources across multiple environments.- Sanitization: There is no mention of sanitizing or validating the output from the argocd commands before the agent processes it.- [DATA_EXPOSURE]: Includes guidance on using argocd login, which involves managing authentication tokens. It also mentions the --insecure flag for development environments, which bypasses TLS verification.

argocd-gitops