theme-factory

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided artifacts (slides, documents) and custom theme descriptions, creating a surface for indirect prompt injection.
  • Ingestion points: Artifact content and user-provided custom theme inputs (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat artifact content as data only.
  • Capability inventory: Reading theme files (themes/*.md) and applying styling to artifacts.
  • Sanitization: No sanitization or validation of input content is described in the instructions.
  • [NO_CODE]: The skill consists entirely of markdown instructions and configuration files, containing no executable code or scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 12:14 PM