Back to skill

Security audit

WeChat Store

Security checks for vulnerabilities and agentic risk

Overview

The store operations have clear approval safeguards, but setup can execute a changing online installer without separate approval.

Review the installation step before use. Prefer a reviewed, pinned CLI installation and require approval for software or bundled-skill changes. OOMOL mediates store access; grant only needed permissions and confirm exact store mutations. The sole bundled artifact was inspected completely, but external installer and connector behavior remains 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 performs remote script installation rather than the declared WeChat Store data operations. Dependency installation can be a supporting implementation detail, but the provided content establishes no relationship between this installer and WeChat Store. The downloaded script is not supplied, so its subsequent behavior 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 pipes a mutable remote script directly into Bash without checking a pinned digest, signature, or reviewed artifact; the PowerShell alternative has the same download-and-execute pattern. Compromise of the distribution endpoint or release process could execute attacker-controlled code with the invoking user's permissions, potentially exposing local files and credentials. HTTPS and the legitimate dependency context reduce suspicion of malicious intent but do not establish installer integrity.

Content

Scanner excerpt · SKILL.md (reported line 114)May include surrounding context.

The setup workflow executes remotely downloaded installation scripts without warning about system changes or obtaining installation approval.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

When the CLI is missing, the workflow instructs the agent to install software without first obtaining approval for local system changes. Authorization to operate a WeChat Store does not necessarily authorize installing executable software; the conditional setup trigger limits exposure but does not establish consent. The declared Bash tool restriction may limit execution in some environments, but the setup instructions should not rely on that restriction as their safety control.

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 135)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