tavily-research

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the tvly command-line tool to perform research tasks, manage authentication, and save reports. Access is scoped to the tvly command via the allowed-tools configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the web during the research process, which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: Web content and research results retrieved via the tvly research command (SKILL.md).
  • Boundary markers: None explicitly defined in the prompt instructions to separate untrusted web content from agent instructions.
  • Capability inventory: The skill can execute shell commands through the tvly binary and write output to the local filesystem (SKILL.md).
  • Sanitization: The skill does not specify any sanitization or validation of the data retrieved from external web sources before presenting it to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 10:56 PM