The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Lemlist campaigns and leads, which could potentially contain malicious instructions for the agent.
Ingestion points: Data is ingested via LEMLIST_GET_LIST_CAMPAIGNS (campaign metadata) and LEMLIST_GET_EXPORT_CAMPAIGN_LEADS (lead details) in SKILL.md.
Boundary markers: There are no explicit instructions to use delimiters or ignore embedded content in the ingested data.
Capability inventory: The skill possesses write capabilities including lead enrollment (LEMLIST_POST_CREATE_LEAD_IN_CAMPAIGN), variable enrichment (LEMLIST_POST_ADD_VARIABLES_TO_LEAD), and lead removal (LEMLIST_DELETE_UNSUBSCRIBE_LEAD_FROM_CAMPAIGN).
Sanitization: No sanitization or validation logic is specified for the data retrieved from external sources before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill requires the user to add a remote Model Context Protocol (MCP) server from https://rube.app/mcp as part of the setup process in SKILL.md.

Lemlist Automation