skills/tavily-ai/skills/tavily-cli/Gen Agent Trust Hub

tavily-cli

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides a command to download and execute an installation script from the official vendor domain (cli.tavily.com). This is the standard installation method for the Tavily CLI tool.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run tvly commands for environment setup, authentication, and web search operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that involves ingesting untrusted data from the web, which is the primary purpose of the tool. This introduces a surface for indirect prompt injection if retrieved web pages contain malicious instructions.
  • Ingestion points: Web content retrieved via search, extract, map, crawl, and research commands (SKILL.md).
  • Boundary markers: None present.
  • Capability inventory: Shell command execution and file system access (writing output to files/directories) via the tvly tool.
  • Sanitization: None present.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:06 PM
Security Audit — agent-trust-hub — tavily-cli