tavily-search

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs its intended function of web searching without any malicious patterns. It utilizes the official tavily-python client library to interact with the Tavily API.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of a Python script to perform searches. The script uses the argparse library to safely handle user-supplied search queries as command-line arguments.
  • [EXTERNAL_DOWNLOADS]: The skill involves fetching content from the public internet via the Tavily API. It also includes instructions to install the tavily-python package from the official Python Package Index (PyPI), which is a standard procedure for this type of tool.
  • [SAFE]: There is a potential risk of indirect prompt injection due to the ingestion of untrusted content from search results. This is an inherent characteristic of any internet-connected search tool and does not represent a security vulnerability within the skill itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 11:48 AM