aura-theme

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it instructs the agent to interpret free-form user descriptions and use that interpretation to create or modify files in the user's workspace.
  • Ingestion points: The agent takes free-form natural language descriptions from the user to define theme properties (e.g., colors, mood, density).
  • Boundary markers: There are no explicit instructions to use delimiters or ignore potentially malicious instructions embedded within the user's theme description.
  • Capability inventory: The agent has the ability to search for files (**/styles.css), create new CSS files, and modify existing files by prepending @import statements.
  • Sanitization: The skill lacks instructions for validating or sanitizing the content derived from user input before it is written into CSS files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 06:14 AM
Security Audit — agent-trust-hub — aura-theme