UTC
High

Grackle: Fail-open authorization in the MCP tool layer lets scoped agents perform cross-task and cross-session mutations (IDOR)

GHSA-f9ff-5x35-7gfw · published 2026-07-02

Severity
High
CVSS score
8.7
Chance of exploitation (EPSS)
No CVE
Fixed in
No fix yet
What it is

Authorization for scoped (agent) MCP callers is enforced inline, per tool, and is applied inconsistently — several mutating tools silently omit the ancestry/workspace check that their siblings perform. Because the MCP server authenticates all outbound gRPC with the full server API key and the backend gRPC handlers perform no caller-based authorization, the MCP tool layer is the sole authorization boundary. A malicious or prompt-injected scoped agent can therefore perform cross-task and cross-session operations it should not be allowed to (an IDOR / privilege-boundary bypass). This advisory bundles the audit's Systemic Pattern A findings: F2, F6, F7, F12 (and the duplicate F19).

What to do

No fixed release is listed yet for @grackle-ai/mcp. Limit what it can reach, or stop using it until a fix ships, and follow the source advisory for updates.

Systemic fix: enforce scope centrally in the CallToolRequest dispatcher (mcp-server.ts) via a per-tool targetTaskIdArg / targetSessionIdArg descriptor so any tool that targets a task/session fails closed unless the caller is an ancestor (or self). Immediately, add assertCallerIsAncestor (or self-or-ancestor) to task_update, task_delete, task_resume, session_kill, session_resume, mirroring task_complete/task_start. F7: do not fail open on empty workspaceId — treat a scoped non-root caller with no workspace as having access to no workspace; apply the task_show membership check whenever the caller is scoped and not ROOT_TASK_ID; add a per-id membership check to schedule_show. …

Affected
PackageRegistryAffectedFixed in
@grackle-ai/mcpnpm<= 0.132.1No fix yet

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].