The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources (Kit subscriber and broadcast data) and possesses impactful capabilities.\n
Ingestion points: Subscriber data retrieved via KIT_LIST_SUBSCRIBERS and broadcast content via KIT_LIST_BROADCASTS as described in SKILL.md.\n
Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for processing external data.\n
Capability inventory: The skill uses tools with side effects, including KIT_DELETE_SUBSCRIBER, KIT_DELETE_BROADCAST, and KIT_TAG_SUBSCRIBER.\n
Sanitization: There is no evidence of data sanitization or validation before using external content in the agent's context.\n- [EXTERNAL_DOWNLOADS]: The skill requires connection to an external MCP server endpoint at https://rube.app/mcp to function.\n- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any scripts or executable files.

convertkit-automation