The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, including website URLs and client documents, to generate email copy and campaign configurations.
Ingestion points: Website content research and campaign strategy documents are used as primary inputs in Step 1.
Boundary markers: The instructions lack explicit boundary markers or warnings for the agent to ignore instructions embedded within the external data.
Capability inventory: The skill writes a variants.yaml file to the local file system and invokes the /smartlead-campaign-upload-public tool to initiate campaign uploads.
Sanitization: There is no evidence of sanitization or validation of the ingested data to prevent embedded instructions from altering the agent's behavior.
[COMMAND_EXECUTION]: The skill is designed to interact with and trigger other agent tools and skills.
Evidence: The skill explicitly instructs the agent to run /spam-word-checker and /smartlead-campaign-upload-public as part of its operational flow.
Evidence: The skill references other integration tools like /prospeo-full-export and /disco-like for list-building workflows.

campaign-copywriting