Security audit
Microsoft SharePoint
Security checks for vulnerabilities and agentic risk
Overview
This SharePoint skill is a disclosed Maton/Microsoft Graph integration with sensitive access, but its behaviors are coherent with SharePoint automation and guarded by approval and least-privilege instructions.
Install only if you want Maton-mediated SharePoint access. Review requested Microsoft/Maton scopes carefully, prefer read-only and specific connections, confirm any write/delete/share action, and be especially cautious with triggers or destinations because they can keep forwarding future event data until removed.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.