skills/l-yifan/skills/llamaindex/Gen Agent Trust Hub

llamaindex

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as documentation and a reference guide for the LlamaIndex framework. It contains markdown instructions and Python code snippets for learning purposes.
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of official library packages such as llama-index, openai, and anthropic from PyPI. These are well-known, trusted industry-standard packages.
  • [CREDENTIALS_UNSAFE]: Code examples for database and cloud service integrations (e.g., PostgreSQL, Pinecone) use clear placeholders like user:pass@localhost and your-key. No real credentials or secrets are exposed.
  • [PROMPT_INJECTION]: Prompt templates included in the documentation (e.g., the qa_prompt) follow safety best practices by instructing the LLM to answer only based on provided context and to admit when information is missing.
  • [DATA_EXFILTRATION]: While the skill describes data ingestion from web and GitHub sources, these are standard functionalities of the LlamaIndex tool and are documented here purely for educational use.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 08:29 AM