rico-ui-ux-themes
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a feature to generate themes by fetching content from external URLs, as seen in Options C and D of the interaction workflow.
- Ingestion points: The
webReadertool is instructed to fetch content from user-specified or industry reference URLs (e.g., stripe.com). - Boundary markers: There are no explicit instructions or delimiters to isolate the agent from potentially malicious instructions hidden in the fetched HTML or markdown content.
- Capability inventory: The skill utilizes
ReadandWrite/Edittools to modify local project files and save global theme configurations to~/.rico/themes/. - Sanitization: The instructions do not specify any validation or sanitization of the content extracted from external websites before it is used to influence code generation.
- [COMMAND_EXECUTION]: The skill is designed to execute specific agent tools to perform file system and network operations.
- Evidence:
SKILL.mdidentifies the use ofwebReaderfor fetching URLs andRead/Writetools for code operations. - Mitigation: The skill includes 'CRITICAL EXECUTION RULES' that mandate user selection from a menu and explicit confirmation before the agent executes any changes or output.
Audit Metadata