animation-style-consistency-by-1diwzmp
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from URLs listed in the references.
- Ingestion points: The agent is instructed to read
references/cases.mdand inspect linked media (images and videos) using available tools. - Boundary markers: There are no explicit delimiters or specific instructions provided to the agent to ignore potentially malicious embedded commands within the external content.
- Capability inventory: The agent uses image/video inspection and browser tools to analyze content and generates text-based video prompts. No shell execution, file-writing, or network exfiltration capabilities are linked to the processing of this data.
- Sanitization: No sanitization, escaping, or filtering of the external content is described before interpolation into the agent's context.
- [EXTERNAL_DOWNLOADS]: The skill references and requires the inspection of external media and case summaries hosted on
goodcase.aiandmedia.goodcase.ai. It also provides links to primary sources onx.com. The agent is directed to use browser or media tools to fetch and analyze this external content as part of the core style consistency workflow.
Audit Metadata