The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external sources, such as third-party documentation and model outputs, which introduces a surface for instructions embedded in external content to influence agent behavior.
Ingestion points: Data enters the agent's context through the outputs of sandbase_run and sandbase_run_get as described in references/sandbase-api-map.md.
Boundary markers: The instructions lack specific requirements for using delimiters or boundary markers to differentiate between system instructions and external data.
Capability inventory: The skill possesses the capability to execute external functions and read file contents across the repository through the sandbase_run tool.
Sanitization: There are no specific instructions for sanitizing, filtering, or validating the content retrieved from external API calls before it is processed.
[COMMAND_EXECUTION]: The skill utilizes a suite of tools (sandbase_run, sandbase_discover, etc.) to execute external capabilities provided by the vendor (sandbaseai). While these tools allow for dynamic execution of tasks, the skill implements safety checks including cost transparency, user confirmation for paid calls, and an emphasis on sending the minimum necessary data.

turborepo