theme-factory

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill allows the generation of custom themes based on user-provided descriptions, which introduces a potential attack surface for indirect prompt injection if malicious instructions are provided in the input data.
  • Ingestion points: User-provided inputs and descriptions for custom theme creation as specified in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between theme descriptions and potential malicious commands within the user input.
  • Capability inventory: The skill's capabilities include reading theme configurations and applying visual styles (hex colors and font names) to artifacts.
  • Sanitization: The skill lacks defined sanitization or validation mechanisms for external inputs used in theme generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:05 PM
Security Audit — agent-trust-hub — theme-factory