Back to skill

Security audit

WeChat Official Account

Security checks for vulnerabilities and agentic risk

Overview

The WeChat controls are sensible, but setup can execute unchecked remote code and introduce additional agent skills without clearly explaining those changes.

Review and approve CLI setup separately, preferably using a verified, pinned release. Check which additional agent skills it installs and how to disable automatic synchronization. OOMOL will mediate account operations and hold connected credentials. Keep payload approval enabled for publishing, messaging, and deletion. The bundled instructions were fully reviewed, but the remote installers and hosted runtime 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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied chunk performs remote software installation rather than any visible WeChat Official Account operation. Installing a dependency could be a supporting implementation detail, but this chunk establishes no relationship between the external installer and the declared functionality. The downloaded script's contents and subsequent behavior cannot be determined from the supplied code.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup command pipes a remotely fetched, unpinned script directly into Bash without prior inspection or independent integrity verification; the PowerShell alternative has the same weakness. Although this is a legitimate dependency-installation workflow triggered only when the CLI is missing, compromise of the distribution endpoint could execute arbitrary code with the local user's privileges, exposing accessible files and credentials.

Content

Scanner excerpt · SKILL.md (reported line 96)May include surrounding context.

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 117)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