The Agent Skills Directory

[SAFE]: The skill uses the official together Python SDK and together-ai Node.js package to interact with Together AI's well-known API endpoints.
[SAFE]: Sensitive credentials like API keys are managed through environment variables (TOGETHER_API_KEY), which is a standard security best practice.
[PROMPT_INJECTION]: The skill implements a Retrieval-Augmented Generation (RAG) pipeline, which is a common surface for indirect prompt injection attacks where malicious content in indexed documents could influence the agent's behavior. \n
Ingestion points: The VectorStore.add method in scripts/rag_pipeline.py accepts external text data to be indexed. \n
Boundary markers: The system prompt in rag_query uses a "Context:" label to delimit retrieved information. \n
Capability inventory: The pipeline uses client.chat.completions.create to generate responses based on the context. \n
Sanitization: No explicit sanitization or filtering of the retrieved content is performed before interpolation into the prompt.

together-embeddings