GHSA-647h-p824-99w7 @grackle-ai/mcp has a workspace authorization bypass in its knowledge_search MCP tool

Not scored Published

A scoped agent can bypass workspace isolation to read knowledge graph data from other workspaces by supplying an arbitrary workspace ID.

Exploited in the wild
Not known
Login needed
Any signed-in user
Attackable
Over the internet
Victim action needed
Not needed
Fix
Available

What is GHSA-647h-p824-99w7?

GHSA-647h-p824-99w7 is a missing authorization vulnerability in @grackle-ai/mcp, published on 25 Mar 2026. Any signed-in user can exploit it over the network, with no action from the victim.

Official description

Impact

The knowledge_search and knowledge_get_node MCP tools are included in SCOPED_TOOLS (visible to scoped agents) but their handlers do not receive authContext and do not enforce workspace scoping. A scoped agent in Workspace A can supply an arbitrary workspaceId parameter to search or retrieve knowledge graph nodes from Workspace B, bypassing workspace isolation boundaries.

This is a cross-workspace data leakage vulnerability affecting any deployment where multiple workspaces contain sensitive knowledge graph data and scoped agents are used.

Affected code:

  • packages/mcp/src/tools/knowledge.ts:146-169 (knowledge_search handler)
  • packages/mcp/src/tools/knowledge.ts:244-283 (knowledge_get_node handler)
  • packages/mcp/src/tool-scoping.ts:11 (both tools listed in SCOPED_TOOLS)

Contrast with correct implementation: knowledge_create_node (same file, lines 334-357) properly receives authContext and overrides the user-supplied workspaceId for scoped callers.

Design Note

Cross-workspace knowledge sharing is a legitimate future feature — agents working across different repos may need to collaborate and share knowledge. However, this access should be opt-in with explicit grants, not an implicit bypass. The immediate fix locks scoped agents to their own workspace. A future design could introduce:

  • Workspace-level "share knowledge with" settings
  • A cross_workspace scope on scoped tokens
  • Explicit workspaceIds (plural) in the auth context

Patches

Fix: Add authContext parameter to knowledge_search and knowledge_get_node handlers and enforce workspace scoping, matching the pattern in knowledge_create_node:

const resolvedWorkspaceId =
  authContext?.type === "scoped"
    ? authContext.workspaceId ?? ""
    : workspaceId ?? "";

When cross-workspace collaboration is designed, this check can be relaxed intentionally with proper access controls.

Workarounds

Do not use scoped agent tokens in multi-workspace deployments until patched. Alternatively, remove knowledge_search and knowledge_get_node from the SCOPED_TOOLS set in tool-scoping.ts.

References

  • CWE-284: Improper Access Control
  • File: packages/mcp/src/tools/knowledge.ts
  • File: packages/mcp/src/tool-scoping.ts

Which versions are affected by GHSA-647h-p824-99w7?

2 open source packages ship an affected version, including @grackle-ai/mcp.

PackageAffectedFixed in
@grackle-ai/mcp npmAll versions0.70.2
@grackle-ai/mcp npmAll versions0.70.2

How do I fix GHSA-647h-p824-99w7?

Upgrade @grackle-ai/mcp to 0.70.2 or later.

Upgrade, and check permissions on every request on the server, not only in the interface. More about Missing authorization.

Is GHSA-647h-p824-99w7 being exploited?

There is no known exploitation of GHSA-647h-p824-99w7 in the wild and no public exploit code.

Sources

Is GHSA-647h-p824-99w7 in your software?

Upload an SBOM and sbomify checks it against every vulnerability here, every day.

Check your SBOMs for free