The Agent Skills Directory

[NO_CODE]: The skill consists exclusively of markdown documentation and usage examples. No executable scripts, binaries, or active configuration files are present in the skill folder.
[PROMPT_INJECTION]: The documentation describes a Retrieval-Augmented Generation (RAG) workflow which has an inherent risk of indirect prompt injection. Ingestion points: Data is fetched from external vector databases like Pinecone and FAISS (SKILL.md). Boundary markers: The example code snippets for prompt construction do not include delimiters or instructions to the model to ignore embedded commands in the retrieved context. Capability inventory: The skill defines high-level integration with AI models and external data stores but contains no code to execute these capabilities locally. Sanitization: There is no mention of sanitizing or validating retrieved data before it is interpolated into prompts.

rag