The Agent Skills Directory

[COMMAND_EXECUTION] (LOW): The skill utilizes the curl utility to interact with the Tavily REST API. While the commands are structured for specific API endpoints, the use of shell commands for network operations represents a higher capability surface than native library calls.
[DATA_EXFILTRATION] (LOW): Network operations are directed to api.tavily.com. This domain is not on the trusted whitelist; however, this communication is required for the skill's primary purpose. No evidence of sensitive local file access was found.
[PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection because it ingests untrusted data from the public internet. Ingestion points: Search results and scraped content from search, extract, and crawl tools (defined in SKILL.md). Boundary markers: None; the skill does not define delimiters to separate web data from agent instructions. Capability inventory: Execution of curl for external network requests. Sanitization: None; the skill passes content directly from the API to the agent context.

tavily