Back to skill

Security audit

Microsoft Teams

Security checks for vulnerabilities and agentic risk

Overview

The Teams functions are clearly scoped, but setup can execute an unverified installer and introduce broader agent changes without clear user approval.

Review the software setup separately before allowing this skill to install anything. Prefer a verified, pinned CLI release and disable automatic skill synchronization if you do not want other agent skills changed. Limit the connected Teams account's permissions and retain the required confirmation before sending messages. The remote installer and hosted connector implementation were not verified.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code performs remote software installation, not Microsoft Teams data operations. Nothing in the chunk establishes that this installer is a supporting dependency for Teams functionality. The downloaded script's contents and any further effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a live remote script directly into Bash executes its contents without a pinned version or independent integrity verification; the PowerShell alternative has the same weakness. Compromise of the distribution endpoint or release pipeline could therefore execute attacker-controlled code with the agent's local privileges, although the legitimate dependency context provides no evidence of malicious intent.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

Fallback setup executes downloaded installation scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback directs the agent to execute a downloaded installer without first obtaining explicit approval for local code execution and system changes. Restricting installation to a missing-CLI error reduces exposure, but a Teams request can still trigger execution outside the requested service operation with the agent's local privileges.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources