The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data that could contain malicious instructions.
Ingestion points: The skill fetches subscriber data via KIT_LIST_SUBSCRIBERS and full email content via KIT_GET_BROADCAST (referenced in SKILL.md).
Capability inventory: The skill includes high-impact tools such as KIT_DELETE_SUBSCRIBER and KIT_DELETE_BROADCAST which could be abused if the agent inadvertently follows instructions embedded in fetched data.
Boundary markers: No specific boundary markers or "ignore previous instructions" delimiters are provided for the data processed from the Kit API.
Sanitization: There is no documentation or instruction for sanitizing or escaping the content retrieved from external broadcasts before the agent processes it.

convertkit-automation