ClawHub
Back to skill

Security audit

microsoft-teams

Security checks for vulnerabilities and agentic risk

Overview

This Microsoft Teams skill gives an agent documented access to Teams through Maton, with sensitive operations disclosed and gated by user approval.

Install only if you are comfortable authorizing Maton to act on your Microsoft Teams data. Keep OAuth scopes narrow, confirm every message send, meeting change, deletion, function, trigger, or destination, and avoid raw API keys unless the CLI cannot be used.

A.I.G

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

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest says this skill is for Microsoft Teams actions and explicitly states Microsoft Teams is not an event source, while this file documents Notion event types and scoping for monitoring Notion pages and comments. Even though the file says it is shared platform reference text, it still embeds a separate third-party event-source capability that is not justified by the stated purpose of a Teams integration skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.