Back to skill

Security audit

WeCom MCP

Security checks for vulnerabilities and agentic risk

Overview

The WeCom workflow includes clear approval controls, but its setup instructions can trigger unverified remote code execution without separate approval.

Install and verify a specific CLI release yourself before using this skill, and prevent automatic execution of its installer fallback. Review the CLI's agent-skill installation behavior and the permissions granted through OOMOL. Keep explicit approval for WeCom changes. The supplied artifact shows no malicious intent, but the external installer payload and its exact local changes remain unverified.

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
95% confidence
Finding

The supplied chunk executes an installer hosted on cli.oomol.com, not a WeCom MCP operation. Dependency installation can be a supporting implementation detail, but the supplied content establishes no relationship between this installer and the declared WeCom functionality. The downloaded script's contents are not supplied, so its further behavior and safety cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command immediately executes mutable remote content without a pinned version or independently verified integrity; the PowerShell alternative has the same issue. A compromised installer endpoint or publishing pipeline could execute arbitrary code with the agent's local privileges, although the dependency-setup context and conditional trigger provide no evidence of malicious intent.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

The setup workflow executes a downloaded installer without warning about local system changes or obtaining approval.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The missing-command fallback instructs the agent to install software without first obtaining approval for local system changes. Although conditional and connected to a legitimate dependency, this can expand a request to operate WeCom into executing installation code with the agent's local permissions; the declared tool allowlist may constrain execution but does not make the instruction safe.

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 77)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