GHSA-f9ff-5x35-7gfw: Grackle: Fail-open authorization in the MCP tool layer lets scoped agents perform cross-task and cross-session mutations (IDOR)
The @grackle-ai/mcp package (version 0.132.1 and earlier) contains multiple authorization bypass vulnerabilities due to inconsistent enforcement of scoped agent permissions in the MCP tool layer. The MCP server authenticates outbound gRPC calls with a full server API key, but backend handlers do not enforce caller-based authorization, relying solely on the MCP tool layer for access control. Several mutating tools fail to verify caller ancestry or workspace membership, allowing scoped agents to perform unauthorized cross-task and cross-session mutations, including task deletion, updates, session termination, and resumption. Additionally, scoped tokens without workspace association fail open, enabling read-only cross-workspace data disclosure. The scoped-token revocation mechanism is ineffective as it is never invoked outside tests and uses in-memory storage only. These issues collectively represent a high-severity risk of privilege boundary bypass and unauthorized data access or modification.
AI Analysis
Technical Summary
Authorization for scoped MCP callers is enforced inconsistently at the MCP tool layer, which is the sole authorization boundary since backend gRPC handlers accept requests authenticated with the full server API key but perform no caller-based authorization. Several mutating tools (task_update, task_delete, task_resume, session_kill, session_resume) omit ancestry/workspace checks, allowing scoped agents to perform cross-task and cross-session operations they should not be authorized for, constituting an IDOR and privilege boundary bypass. Workspaceless scoped tokens fail open, allowing read-only cross-workspace data access. The scoped-token revocation API is dead code, providing no effective token revocation. The root cause includes setting the full server API key on outbound gRPC calls and lack of centralized scope enforcement. The advisory recommends systemic fixes to enforce scope centrally and immediate addition of ancestry checks to vulnerable tools.
Potential Impact
Scoped agents can bypass authorization controls to perform unauthorized mutations across tasks and sessions, including deleting or updating tasks belonging to other agents or workspaces, and terminating or resuming sessions they do not own. This leads to privilege boundary bypass, potential data loss, and denial of service against sibling or parent agents. Workspaceless scoped tokens allow read-only disclosure of all tasks across all workspaces. The ineffective token revocation means compromised scoped tokens remain valid for their full lifetime, increasing risk of persistent unauthorized access.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. The advisory recommends a systemic fix to enforce scope centrally in the MCP tool request dispatcher, ensuring any tool targeting a task or session fails closed unless the caller is an ancestor or self. Immediate mitigation includes adding ancestry checks (assertCallerIsAncestor) to all mutating tools lacking them (task_update, task_delete, task_resume, session_kill, session_resume). Scoped tokens without workspace association should be treated as having no workspace access, enforcing membership checks on all relevant tools. The scoped-token revocation mechanism should be integrated into task lifecycle flows with persistent storage or removed if unused. Until fixes are applied, restrict use of scoped agents and monitor for unauthorized cross-task or cross-session operations.
GHSA-f9ff-5x35-7gfw: Grackle: Fail-open authorization in the MCP tool layer lets scoped agents perform cross-task and cross-session mutations (IDOR)
Description
The @grackle-ai/mcp package (version 0.132.1 and earlier) contains multiple authorization bypass vulnerabilities due to inconsistent enforcement of scoped agent permissions in the MCP tool layer. The MCP server authenticates outbound gRPC calls with a full server API key, but backend handlers do not enforce caller-based authorization, relying solely on the MCP tool layer for access control. Several mutating tools fail to verify caller ancestry or workspace membership, allowing scoped agents to perform unauthorized cross-task and cross-session mutations, including task deletion, updates, session termination, and resumption. Additionally, scoped tokens without workspace association fail open, enabling read-only cross-workspace data disclosure. The scoped-token revocation mechanism is ineffective as it is never invoked outside tests and uses in-memory storage only. These issues collectively represent a high-severity risk of privilege boundary bypass and unauthorized data access or modification.
CVSS v4.0
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
Authorization for scoped MCP callers is enforced inconsistently at the MCP tool layer, which is the sole authorization boundary since backend gRPC handlers accept requests authenticated with the full server API key but perform no caller-based authorization. Several mutating tools (task_update, task_delete, task_resume, session_kill, session_resume) omit ancestry/workspace checks, allowing scoped agents to perform cross-task and cross-session operations they should not be authorized for, constituting an IDOR and privilege boundary bypass. Workspaceless scoped tokens fail open, allowing read-only cross-workspace data access. The scoped-token revocation API is dead code, providing no effective token revocation. The root cause includes setting the full server API key on outbound gRPC calls and lack of centralized scope enforcement. The advisory recommends systemic fixes to enforce scope centrally and immediate addition of ancestry checks to vulnerable tools.
Potential Impact
Scoped agents can bypass authorization controls to perform unauthorized mutations across tasks and sessions, including deleting or updating tasks belonging to other agents or workspaces, and terminating or resuming sessions they do not own. This leads to privilege boundary bypass, potential data loss, and denial of service against sibling or parent agents. Workspaceless scoped tokens allow read-only disclosure of all tasks across all workspaces. The ineffective token revocation means compromised scoped tokens remain valid for their full lifetime, increasing risk of persistent unauthorized access.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. The advisory recommends a systemic fix to enforce scope centrally in the MCP tool request dispatcher, ensuring any tool targeting a task or session fails closed unless the caller is an ancestor or self. Immediate mitigation includes adding ancestry checks (assertCallerIsAncestor) to all mutating tools lacking them (task_update, task_delete, task_resume, session_kill, session_resume). Scoped tokens without workspace association should be treated as having no workspace access, enforcing membership checks on all relevant tools. The scoped-token revocation mechanism should be integrated into task lifecycle flows with persistent storage or removed if unused. Until fixes are applied, restrict use of scoped agents and monitor for unauthorized cross-task or cross-session operations.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-f9ff-5x35-7gfw
- Osv Schema Version
- 1.4.0
- Aliases
- []
- Ecosystems
- ["npm"]
- Database Specific Severity
- HIGH
- Cvss Version
- 4.0
Threat ID: 6a46ecb727e9c7971943ca2e
Added to database: 07/02/2026, 22:56:55 UTC
Last enriched: 07/02/2026, 23:12:07 UTC
Last updated: 07/02/2026, 23:37:20 UTC
Views: 3
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.