The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the recoup research CLI tool to perform research tasks. These commands are executed with various arguments including artist names, entity names, and URLs.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection risk through its web intelligence features. * Ingestion points: External data is fetched using recoup research extract, web, and report commands in SKILL.md. * Boundary markers: There are no specific delimiters or instructions provided to the agent to treat extracted content as untrusted. * Capability inventory: The agent has the ability to execute CLI commands and write research results to the filesystem. * Sanitization: No sanitization or validation steps are defined for the data retrieved from external web sources.

industry-research