Back to skill

Security audit

Sina Finance ZYHub

Security checks for vulnerabilities and agentic risk

Overview

The financial-data functions fit the stated purpose, but automatic setup executes unchecked remote code and can introduce additional agent skills.

Review setup before enabling this skill. Install a verified CLI independently, and consider disabling its managed-skill synchronization using the controls in the [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). OOMOL will mediate queries and hold the connected provider credentials. No malicious payload was established, but the remote installer and connector implementations 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied chunk performs remote software installation rather than the declared financial-data access. Nothing in the chunk establishes this installer as a supporting dependency for ZYHub functionality. The downloaded script's contents are not supplied, so its additional effects cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The supplied code only initiates authentication; it contains no ZYHub-specific search, retrieval, or resource reference. Authentication could be a supporting implementation detail if tied to the declared service, but the supplied chunk provides no evidence of that connection.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The fallback installation command pipes a remotely fetched, unpinned script directly into Bash, allowing the endpoint's response to execute with the agent process's privileges without prior verification or review. A compromised distribution endpoint could therefore compromise local files or credentials; the Windows alternative has the same weakness, although execution is conditional on the CLI being missing.

Content

Scanner excerpt · SKILL.md (reported line 90)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 111)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