The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to operate primarily through the execution of the dce command-line utility to perform administrative and monitoring tasks.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it ingests and processes untrusted data from the platform's backend.
Ingestion points: Data enters the agent's context through commands that query logs and events, such as dce insight log query-log and dce insight event query-events found in references/modules/insight.md.
Boundary markers: The instructions do not define clear delimiters or include specific warnings to the agent to ignore instructions embedded within retrieved data.
Capability inventory: The skill provides access to sensitive operations, including managing user accounts, creating access tokens (dce global-management account create-access-token), and creating SSH keys (dce global-management account create-ssh-key), as documented in references/modules/global-management.md.
Sanitization: The workflow lacks explicit steps for sanitizing or validating external content before the agent processes it.

dce