The Agent Skills Directory

[SAFE]: The skill uses the official opendeploy CLI and targets the vendor's verified domain dashboard.opendeploy.dev for all support operations.
[DATA_EXFILTRATION]: The instructions include robust security guidance, specifically forbidding the agent from posting secrets, private keys, or unredacted customer data to external channels.
[COMMAND_EXECUTION]: Usage of the command line is strictly limited to the official vendor CLI and standard data processing tools like jq. No arbitrary or unvalidated commands are executed.
[PROMPT_INJECTION]: There are no instructions that attempt to bypass safety filters or override the agent's core programming.
[EXTERNAL_DOWNLOADS]: The skill does not perform any remote script downloads or execute code from untrusted external sources.

opendeploy-oncall