ClawHub
Back to skill

Security audit

Yingmi MCP

Security checks for vulnerabilities and agentic risk

Overview

The financial connector has sensible approval rules, but its required CLI can silently install additional agent skills beyond the task’s scope.

Review the CLI’s additional skill installation before use. Its documentation provides OO_SKILLS_SYNC_DISABLED=1 to suppress startup synchronization; configure that before invoking it if you only want the Yingmi connector. Inspect the installer separately, connect only the intended account, and retain the skill’s write-confirmation requirements. The exact distributed CLI, remote installer, and hosted tools were not verified; no malicious intent was established.

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
  • 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
99% confidence
Finding

The supplied code runs a remote installation script rather than performing the declared Yingmi MCP data operations. Nothing provided establishes that this installer is a supporting requirement for Yingmi MCP. The downloaded script's contents and subsequent effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup instructions pipe a remotely fetched, unpinned script directly into Bash; the Windows alternative similarly executes downloaded content with iex. Compromise of the distribution endpoint or installer supply chain could execute arbitrary code with the invoking user's privileges, exposing local files and credentials. Conditional execution only when the CLI is missing reduces exposure but does not establish installer integrity.

Content

Scanner excerpt · SKILL.md (reported line 56)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 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