GHSA-f9ff-5x35-7gfw
Grackle: Fail-open authorization in the MCP tool layer lets scoped agents perform cross-task and cross-session mutations (IDOR)
GHSA-f9ff-5x35-7gfw is a high vulnerability (CVSS 8.7) in @grackle-ai/mcp, published July 2, 2026. No source lists public exploit code. No source names a fixed version.
- Severity
- 8.7 HighCVSS 4.0, GitHub Advisories
- Exploit chance
- UnscoredNo EPSS score yet
- Exploitation
- None knownNot on CISA’s or ENISA’s lists
- Fixed in
- No fix listedNo source names one
Description
Summary
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).
Affected versions
@grackle-ai/mcp (with @grackle-ai/plugin-core / @grackle-ai/auth) at 0.132.1 and earlier.
Root cause
mcp-server.ts:111-127(createGrpcClients) setsAuthorization: Bearer ${apiKey}(the full server key) on every outbound gRPC call.- Backend handlers (
updateTask,deleteTask,resumeTask,killAgent,getTaskinplugin-core) take only the request message — noAuthContext— and act on whatever ID is passed. - Therefore scope must be enforced in each MCP tool handler. Some call
assertCallerIsAncestor(task_complete,task_start,session_attach,session_send_input); their destructive siblings do not. New tools that forget the check fail open.
F2 — task_update / task_delete / task_resume bypass ancestry (High)
Location: packages/mcp/src/tools/task.ts:226 (task_update), :393 (task_delete), :465 (task_resume).
These accept an arbitrary taskId with only a ROOT_TASK_ID special-case and no assertCallerIsAncestor. The central dispatcher hardcodes its workspace gate to name === "task_show", and these tools' Zod schemas have no workspaceId field (so the blanket injection is stripped). They are not in DEFAULT_SCOPED_MCP_TOOLS but are in the shipped ORCHESTRATOR_MCP_TOOLS / ADMIN_MCP_TOOLS presets.
Exploit: a scoped agent under the orchestrator persona learns a sibling/parent/cross-workspace task ID (via task_list/task_search), then task_delete {taskId: <victim>} (permanently destroys another agent's or the human parent's work) or task_update to flip a sibling to complete/failed or rewrite its dependency DAG and budgets.
F6 — session_kill / session_resume bypass ancestry (Medium)
Location: packages/mcp/src/tools/session.ts:95 (session_resume), :178 (session_kill).
Call client.killAgent / client.resumeAgent directly with no auth context, unlike session_attach/session_send_input. session_kill is in the orchestrator preset. Exploit: cross-session SIGKILL DoS against a sibling agent or the root orchestrator; foreign session resume.
F7 — Workspaceless scoped token fails open to all workspaces (Medium)
Location: packages/mcp/src/mcp-server.ts:565-600.
The per-task cross-workspace check (task_show block) is gated on authContext.workspaceId being truthy. A task created without a workspace (a supported config) mints a scoped token with pid: "" → workspaceId: undefined, so the check is skipped and the injected workspaceId becomes "", which the backend treats as "all workspaces." Exploit: a malicious agent in a workspaceless session calls task_list (no args) → reads every task in every workspace, then task_show {taskId} cross-workspace (title/description/branch/review-notes). schedule_show (in the default scoped allowlist) resolves by ID with no workspace check. Read-only cross-workspace disclosure.
F12 — Scoped-token revocation is dead code (Low)
Location: packages/auth/src/scoped-token.ts:23,142-149.
The consuming check is wired (auth-middleware.ts:90-92), but revokeTask() is never called outside tests — no task-abort/stop flow invokes it — and the backing revokedTasks Map is in-memory only (lost on restart). A compromised agent that exfiltrated its scoped token keeps authenticating for the full 24h TTL regardless of task lifecycle.
Remediation
- Systemic fix: enforce scope centrally in the
CallToolRequestdispatcher (mcp-server.ts) via a per-tooltargetTaskIdArg/targetSessionIdArgdescriptor 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) totask_update,task_delete,task_resume,session_kill,session_resume, mirroringtask_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 thetask_showmembership check whenever the caller is scoped and notROOT_TASK_ID; add a per-id membership check toschedule_show. - F12: wire
revokeTask()into task-abort/stop flows with SQLite-backed persistence (like channel-grant revocation), or remove the dead API and document the 24h window. - Add regression tests mirroring the existing
task_completeancestor tests for each mutator.
CWEs
CWE-862 (Missing Authorization), CWE-639 (Authorization Bypass Through User-Controlled Key / IDOR), CWE-613 (Insufficient Session Expiration).
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- Low
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Affected packages
| Package | Affected | Fixed |
|---|---|---|
@grackle-ai/mcpnpm | through 0.132.1 | None known |
@grackle-ai/plugin-corenpm | through 0.132.1 | None known |
@grackle-ai/authnpm | through 0.132.1 | None known |
What each source reports
GitHub Advisories Score used 8.7
Grackle: Fail-open authorization in the MCP tool layer lets scoped agents perform cross-task and cross-session mutations (IDOR)
Summary
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).
Affected versions
@grackle-ai/mcp (with @grackle-ai/plugin-core / @grackle-ai/auth) at 0.132.1 and earlier.
Root cause
mcp-server.ts:111-127(createGrpcClients) setsAuthorization: Bearer ${apiKey}(the full server key) on every outbound gRPC call.- Backend handlers (
updateTask,deleteTask,resumeTask,killAgent,getTaskinplugin-core) take only the request message — noAuthContext— and act on whatever ID is passed. - Therefore scope must be enforced in each MCP tool handler. Some call
assertCallerIsAncestor(task_complete,task_start,session_attach,session_send_input); their destructive siblings do not. New tools that forget the check fail open.
F2 — task_update / task_delete / task_resume bypass ancestry (High)
Location: packages/mcp/src/tools/task.ts:226 (task_update), :393 (task_delete), :465 (task_resume).
These accept an arbitrary taskId with only a ROOT_TASK_ID special-case and no assertCallerIsAncestor. The central dispatcher hardcodes its workspace gate to name === "task_show", and these tools' Zod schemas have no workspaceId field (so the blanket injection is stripped). They are not in DEFAULT_SCOPED_MCP_TOOLS but are in the shipped ORCHESTRATOR_MCP_TOOLS / ADMIN_MCP_TOOLS presets.
Exploit: a scoped agent under the orchestrator persona learns a sibling/parent/cross-workspace task ID (via task_list/task_search), then task_delete {taskId: <victim>} (permanently destroys another agent's or the human parent's work) or task_update to flip a sibling to complete/failed or rewrite its dependency DAG and budgets.
F6 — session_kill / session_resume bypass ancestry (Medium)
Location: packages/mcp/src/tools/session.ts:95 (session_resume), :178 (session_kill).
Call client.killAgent / client.resumeAgent directly with no auth context, unlike session_attach/session_send_input. session_kill is in the orchestrator preset. Exploit: cross-session SIGKILL DoS against a sibling agent or the root orchestrator; foreign session resume.
F7 — Workspaceless scoped token fails open to all workspaces (Medium)
Location: packages/mcp/src/mcp-server.ts:565-600.
The per-task cross-workspace check (task_show block) is gated on authContext.workspaceId being truthy. A task created without a workspace (a supported config) mints a scoped token with pid: "" → workspaceId: undefined, so the check is skipped and the injected workspaceId becomes "", which the backend treats as "all workspaces." Exploit: a malicious agent in a workspaceless session calls task_list (no args) → reads every task in every workspace, then task_show {taskId} cross-workspace (title/description/branch/review-notes). schedule_show (in the default scoped allowlist) resolves by ID with no workspace check. Read-only cross-workspace disclosure.
F12 — Scoped-token revocation is dead code (Low)
Location: packages/auth/src/scoped-token.ts:23,142-149.
The consuming check is wired (auth-middleware.ts:90-92), but revokeTask() is never called outside tests — no task-abort/stop flow invokes it — and the backing revokedTasks Map is in-memory only (lost on restart). A…
- Record
GHSA-f9ff-5x35-7gfw- CVSS 4.0
- 8.7 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N - Weakness
- CWE-613, CWE-639, CWE-862
- Updated
- 2026-11-02
OSV 8.7
Grackle: Fail-open authorization in the MCP tool layer lets scoped agents perform cross-task and cross-session mutations (IDOR)
Summary
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).
Affected versions
@grackle-ai/mcp (with @grackle-ai/plugin-core / @grackle-ai/auth) at 0.132.1 and earlier.
Root cause
mcp-server.ts:111-127(createGrpcClients) setsAuthorization: Bearer ${apiKey}(the full server key) on every outbound gRPC call.- Backend handlers (
updateTask,deleteTask,resumeTask,killAgent,getTaskinplugin-core) take only the request message — noAuthContext— and act on whatever ID is passed. - Therefore scope must be enforced in each MCP tool handler. Some call
assertCallerIsAncestor(task_complete,task_start,session_attach,session_send_input); their destructive siblings do not. New tools that forget the check fail open.
F2 — task_update / task_delete / task_resume bypass ancestry (High)
Location: packages/mcp/src/tools/task.ts:226 (task_update), :393 (task_delete), :465 (task_resume).
These accept an arbitrary taskId with only a ROOT_TASK_ID special-case and no assertCallerIsAncestor. The central dispatcher hardcodes its workspace gate to name === "task_show", and these tools' Zod schemas have no workspaceId field (so the blanket injection is stripped). They are not in DEFAULT_SCOPED_MCP_TOOLS but are in the shipped ORCHESTRATOR_MCP_TOOLS / ADMIN_MCP_TOOLS presets.
Exploit: a scoped agent under the orchestrator persona learns a sibling/parent/cross-workspace task ID (via task_list/task_search), then task_delete {taskId: <victim>} (permanently destroys another agent's or the human parent's work) or task_update to flip a sibling to complete/failed or rewrite its dependency DAG and budgets.
F6 — session_kill / session_resume bypass ancestry (Medium)
Location: packages/mcp/src/tools/session.ts:95 (session_resume), :178 (session_kill).
Call client.killAgent / client.resumeAgent directly with no auth context, unlike session_attach/session_send_input. session_kill is in the orchestrator preset. Exploit: cross-session SIGKILL DoS against a sibling agent or the root orchestrator; foreign session resume.
F7 — Workspaceless scoped token fails open to all workspaces (Medium)
Location: packages/mcp/src/mcp-server.ts:565-600.
The per-task cross-workspace check (task_show block) is gated on authContext.workspaceId being truthy. A task created without a workspace (a supported config) mints a scoped token with pid: "" → workspaceId: undefined, so the check is skipped and the injected workspaceId becomes "", which the backend treats as "all workspaces." Exploit: a malicious agent in a workspaceless session calls task_list (no args) → reads every task in every workspace, then task_show {taskId} cross-workspace (title/description/branch/review-notes). schedule_show (in the default scoped allowlist) resolves by ID with no workspace check. Read-only cross-workspace disclosure.
F12 — Scoped-token revocation is dead code (Low)
Location: packages/auth/src/scoped-token.ts:23,142-149.
The consuming check is wired (auth-middleware.ts:90-92), but revokeTask() is never called outside tests — no task-abort/stop flow invokes it — and the backing revokedTasks Map is in-memory only (lost on restart). A…
- Record
GHSA-f9ff-5x35-7gfw- CVSS 4.0
- 8.7 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N - Weakness
- CWE-613, CWE-639, CWE-862
- Updated
- 2026-11-02
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | GitHub Advisories, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
References
Left out here: the rest of 2 source descriptions. The JSON record has them.