veo-video
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install the
mcp-veopackage viapipfrom the official Python Package Index. This utility is a vendor-provided tool for Model Context Protocol (MCP) integration. - [COMMAND_EXECUTION]: The skill contains
curlcommand examples intended for terminal execution to interact with the vendor's API endpoints athttps://api.acedata.cloud. - [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data by accepting user-defined prompts and remote image URLs that are passed to an external AI model.
- Ingestion points:
promptandimage_urlsfields in theSKILL.mdworkflow examples. - Boundary markers: Absent; the instructions do not specify delimiters for isolating user prompts from system instructions.
- Capability inventory: The skill utilizes network operations via
curlto transmit data to API endpoints. - Sanitization: No explicit input validation or prompt sanitization logic is documented within the skill instructions.
Audit Metadata