build-mcp-genmedia

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the official Go toolchain (go.dev) and clones the source code for the MCP servers from the author's official GitHub repository (GoogleCloudPlatform/vertex-ai-creative-studio). These are verified, trusted sources related to the skill's purpose.
  • [COMMAND_EXECUTION]: The skill uses shell scripts to perform standard build operations, including curl, tar, git clone, and go build. These operations are transparent and necessary for the stated purpose of compiling servers from source.
  • [DATA_EXFILTRATION]: No data exfiltration was detected. Network operations are limited to fetching official tools and source code.
  • [CREDENTIALS_UNSAFE]: No hardcoded credentials or unsafe secret handling were detected. The script uses standard environment variables for build paths.
  • [PROMPT_INJECTION]: No attempts to override system prompts or bypass safety guidelines were found in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 08:23 AM
Security Audit — agent-trust-hub — build-mcp-genmedia