Back to skill

Security audit

D365 F&O Developer

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only D365 Finance & Operations developer skill with purpose-aligned examples, not an executing or persistent tool.

Installers should treat this as technical guidance for D365 F&O development. Be careful before using the DELETE or DMF import examples in a real environment, use least-privilege credentials, protect SAS URLs, and test data-changing operations in non-production first.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (3)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/integrations.md (reported line 24)May include surrounding context.

{ "Name": "Updated Name" }

DELETE

DELETE /data/Customers(AccountNumber='DE-001')

text

### Authentication:

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file includes a DELETE example that can remove customer records, but the surrounding documentation provides no warning that the operation is destructive or should be used with care. For markdown files, safety-affecting behaviors that could impact user data should be accompanied by a warning.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The documentation describes triggering an import from a package URL using a SAS URL, which can affect system data and may expose sensitive access if mishandled. The markdown does not include any warning about validating the package source, limiting SAS exposure, or the impact of running imports.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.