theme-factory
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user data to apply styling, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: The skill reads user-supplied documents and slide decks as targets for theme application.
- Boundary markers: The instructions lack specific delimiters or directions to ignore embedded instructions within the user's content.
- Capability inventory: The skill's core function involves reading and potentially modifying user files to apply themes.
- Sanitization: There is no mention of sanitizing or validating the contents of the user's deck before styling.
Audit Metadata