tavily-search
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
tavily-pythonpackage from PyPI, which is a standard requirement for using the Tavily API. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the internet via the Tavily Search API.
- Ingestion points: Data enters the agent context through the search results retrieved by
scripts/search.py. - Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore embedded commands within the search results in
SKILL.md. - Capability inventory: The agent has the capability to execute shell commands and read/write files as part of its general environment, which could be targeted by instructions hidden in search results.
- Sanitization: The script performs basic text trimming but does not sanitize the content for potential prompt injection patterns.
Audit Metadata