llamaindex
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill implements patterns for ingesting untrusted data from various external sources which are then interpolated into LLM prompts.
- Ingestion points: Use of
SimpleWebPageReader,GithubRepositoryReader, andPDFReaderinreferences/data_connectors.mdto pull content from external URLs and files. - Boundary markers: The
PromptTemplateinreferences/query_engines.mduses dashed delimiters (---------------------) to separate context from instructions, which provides some structural separation but is not a security guarantee. - Capability inventory: The agents and query engines use LLMs (OpenAI) to process data and can execute tools like a calculator (
multiplyfunction). - Sanitization: No explicit sanitization, HTML stripping, or content filtering is shown before data is passed to the model.
- External Dependencies (SAFE): The documentation refers to official LlamaIndex reader packages and models.
- Evidence:
pip install llama-index-readers-notioninreferences/data_connectors.mdrefers to a standard community-supported package. - Evidence:
SentenceTransformerRerankinreferences/query_engines.mddownloads models from Hugging Face.
Audit Metadata