make-viral-ad
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill handles user-provided character descriptions which creates a standard ingestion surface. Ingestion points: User input for character attributes and outfits. Boundary markers: Delimiters for untrusted data are not specified in the instructions. Capability inventory: Content generation and financial transactions via credit usage. Sanitization: Mitigated by mandatory human-in-the-loop price confirmation and server-side moderation filters.
- [SAFE]: No malicious behavior or security risks were identified. The skill adheres to safety best practices by ensuring users are fully informed of costs before any credits are deducted.
Audit Metadata