Back to skill

Security audit

Alpha Vantage

Security checks for vulnerabilities and agentic risk

Overview

The Alpha Vantage integration is coherent, but automatic setup can execute changing third-party code and introduce broader agent changes without clear user control.

Keep installation under your control: review a specific CLI release before running it and check whether automatic skill synchronization is wanted. The publisher documents a synchronization-disable option in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Understand that OOMOL mediates account access and may require credits. The concern is setup scope and control; the inspected skill does not show credential theft or destructive behavior.

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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The visible code performs remote software installation, not Alpha Vantage data operations. Nothing in the supplied chunk establishes that this installer is a supporting dependency for the declared purpose. The downloaded script's contents and any further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

The supplied chunk only initiates a CLI login; it does not demonstrate any Alpha Vantage operation or connection. Authentication could be a supporting implementation detail if tied to the declared service, but no such relationship is established here.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping an HTTPS response directly into Bash executes whatever the installation endpoint returns without a review or integrity-verification boundary. A compromised distribution endpoint or malicious installer update could execute code with the agent's privileges, potentially exposing accessible files and credentials; HTTPS alone does not protect against a compromised publisher.

Content

Scanner excerpt · SKILL.md (reported line 98)May include surrounding context.

The setup workflow executes remote installation scripts without warning about local system changes or third-party code execution.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The missing-CLI recovery workflow directs the agent to execute remotely downloaded shell or PowerShell code without an explicit approval step or explanation of local system changes. Restricting setup to a command-not-found error reduces exposure, but an ordinary dependency failure can still trigger code execution with the agent's local privileges.

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 119)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