The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the tvly CLI to perform research and analysis. Invocations are restricted to the tvly binary as specified in the skill's tool configuration.
[INDIRECT_PROMPT_INJECTION]: The skill aggregates and processes information from external web sources, presenting a theoretical attack surface for indirect injection. * Ingestion points: External web content retrieved during the research process as described in SKILL.md. * Boundary markers: The skill does not define specific delimiters to separate untrusted web content from the agent's instructions. * Capability inventory: The skill can execute tvly CLI commands and write structured research reports to the local file system using the -o or --output flags. * Sanitization: There are no explicit sanitization or filtering steps defined in the skill instructions for content fetched from the web.

tavily-research