vercel-automation

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: Surface for indirect prompt injection through untrusted data ingestion.
  • Ingestion points: Untrusted data enters via parameters such as projectId, name, gitSource, and environment variable value within the tool sequences described in SKILL.md.
  • Boundary markers: There are no delimiters or instructions to ignore embedded instructions in the processed data.
  • Capability inventory: The skill utilizes high-impact tools including VERCEL_CREATE_NEW_DEPLOYMENT (triggering builds), VERCEL_ADD_ENVIRONMENT_VARIABLE (writing secrets), and VERCEL_UPDATE_PROJECT (overriding build commands).
  • Sanitization: No sanitization, escaping, or validation logic is specified for the input parameters.
  • [EXTERNAL_DOWNLOADS]: Fetches tool configurations and schemas from the Rube MCP server at https://rube.app/mcp.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 09:21 AM