The Agent Skills Directory

[Metadata Poisoning] (MEDIUM): The metadata field generated_with references 'OpenAI GPT-5.2'. As this model version does not exist, the documentation contains hallucinations or deceptive information regarding its origin and reliability.\n- [Data Exposure & Exfiltration] (LOW): The skill requires outbound network access to api.dataforseo.com and docs.dataforseo.com, which are not included in the trusted domain whitelist. It is designed to handle sensitive API credentials (login and password) via HTTP Basic Auth.\n- [Indirect Prompt Injection] (LOW): The skill's purpose is to ingest and analyze external content (LLM responses and web citations). This provides an attack surface for indirect prompt injection, where malicious instructions within the processed data could attempt to influence the agent's behavior, although the skill's impact is currently limited to data reporting.

dataforseo-ai-optimization-api