2vulnerabilities
- Critical0 (0.0%)
- High2 (100.0%)
- Medium0 (0.0%)
- Moderate0 (0.0%)
- Low0 (0.0%)
grackle-ai-mcp
Ecosystem: npm
Downloads: 1.47 K
- 0CriticalAffects 0 versions
- 2HighAffects 2 versions
- 0MediumAffects 0 versions
- 0ModerateAffects 0 versions
- 0LowAffects 0 versions
Monthly breakdown
- Critical
- High
- Medium
- Moderate
- Low
- 1 vulnerabilities
- Critical: 0
- High: 1
- Medium: 0
- Moderate: 0
- Low: 0
- 1 vulnerabilities
- Critical: 0
- High: 1
- Medium: 0
- Moderate: 0
- Low: 0
Vulnerabilities (2)
Known vulnerabilities affecting grackle-ai-mcp, based on data from OSV.
| ID | Severity | Summary | Affected versions | Published | Source |
|---|---|---|---|---|---|
| GHSA-f9ff-5x35-7gfw | High | 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 bypa |
| GitHub (opens in a new tab) | |
| GHSA-647h-p824-99w7 | High | @grackle-ai/mcp has a workspace authorization bypass in its knowledge_search MCP tool### 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:** - `packa |
| GitHub (opens in a new tab) |
- GHSA-f9ff-5x35-7gfwHighGrackle: Fail-open authorization in the MCP tool layer lets scoped agents perform cross-task and cross-session mutations (IDOR)
<= 0.132.1
## 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 bypa
- GHSA-647h-p824-99w7High@grackle-ai/mcp has a workspace authorization bypass in its knowledge_search MCP tool
< 0.70.2
### 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:** - `packa