13.31 · Excessive Permission Granting

Explore 1 source-supported AI security cases for 13.31 · Excessive Permission Granting in Databricks DASF 3.0, with evidence, scope, and defensive analysis.

Risk category

A client grants an MCP server more permissions than its function requires. Broad scopes, insufficient review, and privilege escalation can give a server unnecessary access. Users may approve the grant without understanding its consequences, increasing the harm a malicious or compromised server can cause.

Official framework source ↗ · Open interactive explorer ↗

Validated Research ·

Amazon Q's MCP Auto-Load Bug Made Cloned Repos a Cloud Credential Risk

Wiz showed that older Amazon Q for VS Code (AWS's AI coding assistant extension) language-server versions automatically loaded workspace MCP (Model Context Protocol, a way for AI assistants to connect to external tools) configuration without consent, letting a malicious repository define a command-backed MCP server that inherited the developer environment and exfiltrated AWS identity data. AWS fixed CVE-2026-12957 in language server 1.65.0 and later.

Why it relates: Wiz disclosed CVE-2026-12957 in Amazon Q Developer for VS Code, where workspace MCP configuration could be auto-loaded without consent, start command-backed MCP servers, inherit developer environment variables, and exfiltrate AWS identity data before AWS fixed the issue in language server 1.65.0. The relevant category is Excessive Permission Granting: A client grants an MCP server more permissions than its function requires.

Wiz disclosed CVE-2026-12957 in Amazon Q Developer for VS Code, where workspace MCP configuration could be auto-loaded without consent, start command-backed MCP servers, inherit developer environment variables, and exfiltrate AWS identity data before AWS fixed the issue in language server 1.65.0.

AIA · Read the full case ↗ · SecureFlow · Read the full case ↗