The Agent Skills Directory

[SAFE]: The skill's primary purpose is marketing research and audience creation within the Meta Ads ecosystem. It follows a safe workflow by performing read-only research first and explicitly waiting for user confirmation before creating any assets.- [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or unauthorized data access patterns were identified. The skill asks the user to provide business-related context (budget, offer) necessary for its function.- [EXTERNAL_DOWNLOADS]: No unauthorized downloads or remote code executions were found. The skill references the author's official website (kelpi.ai), which is a legitimate vendor resource.- [PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters, extract system prompts, or override core agent guidelines.- [COMMAND_EXECUTION]: The skill does not contain any shell commands, scripts, or privilege escalation attempts.- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided offer descriptions to generate targeting keywords. While this is a data ingestion point, the risk is low as the data is used for standard API searches, and the skill includes a human-in-the-loop requirement for all creation actions.

audience-builder