Back to plugin

Security audit

Connect Microsoft 365 to OpenClaw

Security checks for vulnerabilities and agentic risk

Overview

The completed scanner reported no findings, and the verdict is benign, with medium overall confidence; this does not establish that the plugin is risk-free.

The scan completed and reported no findings, but its evidence is limited to the results shown. Before installing, review the plugin’s stated purpose, requested access, and installation details, and grant only access you are comfortable with.

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

SkillSpector was not run because this plugin release contains no bundled skills.

Endor dependency reachability

Checked Nov 16, 2026 · 10:14 PM UTC

No reachable vulnerabilities reported

Endor dependency scan completed.