theme-factory
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via user-defined theme descriptions.
- Ingestion points: User input is accepted for custom theme generation as described in SKILL.md.
- Boundary markers: The instructions lack specific delimiters or warnings to prevent the agent from executing instructions embedded in user-provided theme descriptions.
- Capability inventory: The agent can read theme files and apply styling to slides, docs, and HTML pages.
- Sanitization: No input validation or sanitization mechanisms are defined for the user-provided content.
Audit Metadata