The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes the tvly CLI tool to perform website crawling and bulk page extraction. This usage is aligned with the skill's primary function and is authorized via the allowed-tools configuration.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from arbitrary external websites, creating a surface for indirect prompt injection. * Ingestion points: Web content is fetched from user-provided URLs and processed by the agent through the tvly crawl command output. * Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted web content from agent instructions. * Capability inventory: The skill can perform network operations via tvly and write files to the local filesystem using the --output-dir parameter. * Sanitization: The skill does not provide mechanisms for sanitizing or filtering instructions that might be embedded in the crawled content.

tavily-crawl