The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the deepline CLI to perform prospecting tasks. It executes shell commands to run pre-defined workflows ('plays') and export data to the local file system (e.g., deepline runs export). This is the primary intended function of the skill.
[PROMPT_INJECTION]: The skill processes lead data from external providers like Apollo, which constitutes a surface for indirect prompt injection. If search results (e.g., names or descriptions) contained malicious instructions, they could potentially influence the agent during the display phase.
Ingestion points: Resulting rows from deepline plays run and deepline tools execute commands.
Boundary markers: None mentioned in the instructions for the data being processed.
Capability inventory: Shell command execution and file system writes.
Sanitization: The skill does not define specific validation or sanitization steps for data retrieved from external tools before it is tabulated or exported.

deepline-plays-quickstart