tavily-crawl
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill includes an installation command (
curl -fsSL https://cli.tavily.com/install.sh | bash) to set up the Tavily CLI. This resource is hosted on the official domain of the skill author (tavily.com) and represents a legitimate setup procedure for the vendor's tool. - [EXTERNAL_DOWNLOADS]: Fetches an installation script from the official vendor domain (
cli.tavily.com) to prepare the environment. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to ingest and process data from external websites.
- Ingestion points: External web content retrieved from user-specified URLs via the
tvly crawlcommand. - Boundary markers: None explicitly defined in the skill instructions to separate crawled content from agent instructions.
- Capability inventory: The skill can write extracted data to the local filesystem using the
--output-dirflag. - Sanitization: No explicit sanitization or filtering of crawled content is mentioned.
- This risk is inherent to the primary function of a web crawling tool and is documented here as an architectural surface.
Audit Metadata