epic-fantasy-scifi-spectacle-by-1sduwzc
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes structured data from
references/cases.mdto inform its prompt generation logic, which is a standard surface for indirect injection. - Ingestion points: The file
references/cases.mdcontains summaries and prompt excerpts used as templates. - Boundary markers: The workflow uses a "Preserve / Replace / Avoid" reference contract to clearly delimit which parts of the source material should be maintained and which should be modified based on user input.
- Capability inventory: The skill uses an available browser, image, or video tool to inspect media hosted on
goodcase.aiandx.comto verify visual fidelity. - Sanitization: The skill includes a 'Safety and attribution' section that explicitly prohibits inventing sources, impersonating creators, or making unauthorized account changes.
Audit Metadata