theme-factory
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The 'Create your Own Theme' feature in
SKILL.mdallows users to provide inputs that are used to generate theme specifications. Since the agent is instructed to 'apply' these generated themes to artifacts, it creates a potential surface for indirect prompt injection where malicious instructions could be embedded in the theme descriptions. - Ingestion points: User-provided inputs and descriptions for custom theme generation as defined in
SKILL.md. - Boundary markers: Absent; the skill does not specify delimiters or provide instructions for the agent to distinguish between theme data and potentially malicious instructions.
- Capability inventory: The agent is directed by
SKILL.mdto read theme files and modify artifacts (such as slide decks or documents) to apply visual styles. No external scripts or subprocess execution capabilities are identified in the provided files. - Sanitization: Absent; there is no mention of validating, filtering, or sanitizing the user-supplied inputs or the resulting generated theme content before the application step.
Audit Metadata