ugc-asmr-sensory-format
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for the user to add an external Model Context Protocol (MCP) server hosted at
https://mcp.apimage.org/mcp. This domain is a resource associated with the skill's author. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external assets and user-defined requests, creating a surface for potential indirect prompt injection.
- Ingestion points: The skill ingests
PRODUCT_ASSETfiles and user requests for specific sensory content styles to generate video prompts as seen in theSKILL.mdtemplate. - Boundary markers: There are no explicit delimiters or boundary instructions provided to help the model distinguish between intended instructions and potentially malicious data embedded in the product assets.
- Capability inventory: The skill utilizes the
generate_videotool to produce content, which is a capability that could be influenced by injected data. - Sanitization: The skill does not describe any specific sanitization or validation steps for the input data before it is interpolated into the video generation prompt.
Audit Metadata