theme-factory

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing and styling of user-provided artifacts (e.g., slide decks, documents, and HTML landing pages). This creates a potential surface for indirect prompt injection where malicious instructions embedded within the user content could influence the agent's behavior.
  • Ingestion points: User-provided artifacts as specified in the usage instructions in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or provide warnings to the agent to ignore instructions embedded within the processed artifact content.
  • Capability inventory: The agent is empowered to read the artifacts and apply persistent modifications based on theme specifications stored in the themes/ directory.
  • Sanitization: No procedures for sanitizing, escaping, or filtering artifact content before interpolation or processing are described.
  • [EXTERNAL_DOWNLOADS]: The guide in references/font-pairing-guide.md includes references to fetching typography from Google Fonts. This is a standard integration with a well-known and established public service for web assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:21 PM