theme-foundation

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill instructs the agent to run npx @basiclines/rampa. This command downloads and executes code from the npm registry. The organization '@basiclines' is not a trusted source, making this an unverifiable external dependency with remote execution capabilities.- [COMMAND_EXECUTION] (LOW): The skill constructs shell commands by interpolating user-provided input (<brand-color>). This creates a surface for indirect prompt injection or command injection if the input contains shell metacharacters.
  • Ingestion points: User-provided <brand-color> in the Recipe section of SKILL.md.
  • Boundary markers: Absent; there are no instructions to validate the format of the brand color or use delimiters.
  • Capability inventory: Shell command execution via the npx environment.
  • Sanitization: Absent; the brand color is directly injected into the bash command string without escaping or validation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:32 PM