create-agent-with-sanity-context

Warn

Audited by Snyk on Apr 3, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill creates an MCP HTTP connection at runtime to the Agent Context MCP URL (SANITY_CONTEXT_MCP_URL → https://api.sanity.io/v2026-03-03/agent-context/:projectId/:dataset/:slug) and uses mcpClient.tools() (tool descriptions/instructions) as part of the model's toolset/system context, meaning remote content from that URL directly controls prompts and is required for the skill to run.

Issues (1)

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 3, 2026, 06:32 PM
Issues
1