theme-factory
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's feature for generating custom themes based on user input creates a vulnerability surface for indirect prompt injection attacks. If a user provides malicious instructions disguised as a theme description, the agent might execute those instructions while attempting to 'apply' the generated theme to an artifact.
- Ingestion points: User-provided inputs for the 'Create your Own Theme' process described in SKILL.md.
- Boundary markers: Absent. There are no instructions in the skill files to use delimiters or 'ignore embedded instructions' prompts when handling user-provided theme descriptions.
- Capability inventory: The agent is empowered to apply these themes across various document types (slides, docs, HTML pages), which involves file modification and styling tools.
- Sanitization: Absent. The skill does not provide any validation, filtering, or escaping logic for the user-provided data before it is integrated into the styling process.
Audit Metadata