theme-factory
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- NO_CODE (SAFE): The skill consists entirely of Markdown documentation and contains no scripts or executable binaries.
- DATA_EXFILTRATION (SAFE): No network operations or sensitive data access patterns were identified.
- Indirect Prompt Injection (LOW): The 'Create your Own Theme' feature in SKILL.md identifies a surface for indirect prompt injection as it ingests untrusted user data to influence agent output. 1. Ingestion points: User-provided descriptions for custom themes. 2. Boundary markers: Absent. 3. Capability inventory: Reading local theme files and applying styles to artifacts. 4. Sanitization: Absent.
Audit Metadata