theme-foundation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to download and execute the
@basiclines/rampapackage vianpx. This is a vendor-owned resource belonging to the author's official scope and is a standard dependency for the skill's functionality. - [COMMAND_EXECUTION]: The skill operates by executing shell commands using the
rampaCLI to generate color palettes and CSS variables. - [INDIRECT_PROMPT_INJECTION]: The skill instructions template user-provided brand colors directly into shell commands, which creates a potential surface for command injection if the input is not sanitized by the agent before interpolation.
- Ingestion points: User-provided brand color input variables in
SKILL.md. - Boundary markers: The command examples use double quotes around the color input variable to provide basic containment.
- Capability inventory: Shell execution of the
rampatool vianpx. - Sanitization: The skill does not explicitly instruct the agent to validate that the user input conforms to a valid color format before using it in a shell command.
Audit Metadata