Explore 3 source-supported AI security cases for 13.22 · Excessive Permissions and Scope Creep in Databricks DASF 3.0, with evidence, scope, and defensive analysis.
Risk category
An MCP server requests more authority than its intended function needs, or its privileges expand over time. Overly broad OAuth scopes, file-system access, and API permissions enlarge what a compromised server can do. The issue concerns the server's required and accumulated scope of authority.
pgEdge disclosed independent SQL-injection, read-only-enforcement and bundled-client approval defects affecting versions through 1.0.0 and repaired in 1.1.0. A custom pl-do tool could turn argument data into SQL; query_database could defeat an application-level read-only setting; two client defects skipped write confirmation. Database permissions still bound the resulting actions. The source establishes controlled validation, not a malicious customer breach.
Why it relates: The read-only configuration remains backed by a database identity that can create, change and drop tables.
Each advisory contributes its own route and prerequisites; client confirmation and database authorization are different controls.
Chainstack provides blockchain infrastructure services. Chainstack traced its October 2026 intrusion from a test Grafana instance to an unauthenticated, cluster-admin MCP server, then to production through compromised machine credentials. The investigation found database access, secret theft and several persistence routes. It did not recover individual MCP calls or establish customer-node modification. ARTEX is the operator’s assessment of the attacker’s tooling, not actor attribution.
Why it relates: The MCP service account held cluster-admin, expanding potential effects to secrets, privileged workloads and identity changes.
The relation follows the assessed MCP integration and the documented infrastructure effects; separate observed routes remain separate.
Docker MCP Gateway launches tool servers from container images. CVE-2026-55887 allowed attacker-controlled OCI image metadata to populate privileged runtime fields, which became docker run arguments. The disclosed path can mount the host and Docker socket and run as root. Docker fixed versions before 0.42.2; neither prompt filtering nor no-new-privileges repairs these creation-time grants.
Why it relates: Attacker-chosen runtime metadata expands the MCP container's host access beyond descriptive image data. This is creation-time runtime scope injection, not an OAuth-consent request or gradual scope creep.
Docker Gateway OCI metadata mass assignment and creation-time runtime grants; not MCP message parsing or model-directed tool choice.