GHSA-647h-p824-99w7: @grackle-ai/mcp has a workspace authorization bypass in its knowledge_search MCP tool
Noroxi assessment
Priority: Monitor (action score 0/100)
- The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
- Anyone who can reach it over the internet can trigger it. A low-privileged account is enough. No user action is required. No special conditions are required; it is repeatable.
- Fixed version: @grackle-ai/mcp (npm) 0.70.2.
Low priority for now. Upgrade to @grackle-ai/mcp (npm) 0.70.2 or later.
Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it
Primary sources: OSV
### 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`: ```typescript 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`
- Published
- Mar 25, 2026
- Updated
- Mar 25, 2026
- EPSS
- —
- CWE
- CWE-284
Report tools
Action score
0
Low priority for now.
- CVSS
- 0 / 40 · —
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · —
Get told when this record changes
- Not in KEV: no record of exploitation in the wild
- No public exploit code on record
- A fix has been released
If any of these changes, we'll tell you in the daily email digest.
Is your version affected? Check itNoroxi analysis
What does it mean in your environment?
The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.
We use this product, ask for helpAffected systems
Is your version affected?
Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.
| Vendor | Product | CPE |
|---|---|---|
| npm | @grackle-ai/mcp | pkg:npm/%40grackle-ai/mcp |
Package-level exposure
OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.
| Ecosystem | Package | Affected range | Fix |
|---|---|---|---|
| npm | @grackle-ai/mcp | before 0.70.2 | 0.70.2 |
Same product
npm: all recordsOther highest-scoring records for the same primary product.
- GHSA-f9ff-5x35-7gfwGrackle: Fail-open authorization in the MCP tool layer lets scoped agents perform cross-task and cross-session mutations (IDOR)0Monitor
Remediation
Which version to upgrade to
Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.
| Product / package | Fixed version | Source |
|---|---|---|
| npm:@grackle-ai/mcp | 0.70.2 | Package registry (OSV) |
Exploit status
No known public exploit
No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.
Research context
For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.
Timeline
From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.
No dated events beyond publication.
Not on record for this CVE: EPSS history · patch commit or PR link · researcher credit · variant or chain candidate · public bounty program.
Technical details
Attack conditions
- Anyone who can reach it over the internet can trigger it.
- A low-privileged account is enough.
- No user action is required.
- No special conditions are required; it is repeatable.
If successful
- Confidentiality
- Integrity
- Availability
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- Low
- User interaction
- None
Weakness class (CWE)
CWE-284 · Improper Access ControlCVSS vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:L/SI:L/SA:N
osv
Attack context
MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.
Attack patterns (CAPEC)
- Embedding Scripts within ScriptsCAPEC-19likelihood: High · High
- Malicious Logic InsertionCAPEC-441likelihood: Medium · High
- Modification of Windows Service ConfigurationCAPEC-478likelihood: Low · High
- Malicious Root CertificateCAPEC-479likelihood: Low · Low
- Intent SpoofCAPEC-502
- WebView ExposureCAPEC-503
- Data Injected During ConfigurationCAPEC-536likelihood: Low · High
- Incomplete Data Deletion in a Multi-Tenant EnvironmentCAPEC-546likelihood: Low · Medium
ATT&CK techniques
- RootkitT1014
- Obfuscated Files or Information: Embedded PayloadsT1027.009
- Boot or Logon Initialization ScriptsT1037
- Taint shared contentT1080
- Server Software Component: Terminal Services DLLT1505.005
- Pre-OS Boot:BootkitT1542.003
- Create or Modify System ProcessT1543
- Create or Modify System Process: Launch AgentT1543.001
- Create or Modify System Process:Windows ServiceT1543.003
- Create or Modify System Process: Launch DaemonT1543.004
- Event Triggered Execution:Change Default File AssociationT1546.001
- Event Triggered Execution:.bash_profile and .bashrcT1546.004
- Event Triggered Execution: Accessibility FeaturesT1546.008
- Event Triggered Execution: Installer PackagesT1546.016
- Boot or Logon Autostart ExecutionT1547
- Boot or Logon Autostart Execution:Kernel Modules and ExtensionsT1547.006
Change log (2)
- Fix✗ → ✓
- CVSS8 → —
For records you follow, these changes also arrive as notifications. →
References
Show all references (1 more)Show less
Vendor advisories and official records. Exploit/PoC links are deliberately left out.