llamaindex
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a Retrieval-Augmented Generation (RAG) pattern, which by design involves ingesting untrusted external documents from local directories to provide context to an LLM.\n
- Ingestion points: The skill uses
SimpleDirectoryReaderto load data from./dataand./data/knowledge_baseas shown inSKILL.md.\n - Boundary markers: The provided code snippets do not explicitly include prompt delimiters or system instructions to ignore potential commands embedded within the ingested documents.\n
- Capability inventory: The skill focus is limited to data indexing, retrieval, and response synthesis; there are no capabilities for writing to the filesystem, executing system commands, or performing arbitrary network operations beyond model invocation.\n
- Sanitization: No sanitization or filtering logic for the ingested content is present in the examples.\n- [SAFE]: The skill utilizes official LlamaIndex modular packages and follows documented standards for configuring global settings and query engines.
Audit Metadata