skills/acedatacloud/skills/veo-video/Gen Agent Trust Hub

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-veo package via pip from the official Python Package Index. This utility is a vendor-provided tool for Model Context Protocol (MCP) integration.
  • [COMMAND_EXECUTION]: The skill contains curl command examples intended for terminal execution to interact with the vendor's API endpoints at https://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: prompt and image_urls fields in the SKILL.md workflow 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 curl to transmit data to API endpoints.
  • Sanitization: No explicit input validation or prompt sanitization logic is documented within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 03:01 PM