Back to skill

Security audit

The Odds API

Security checks for vulnerabilities and agentic risk

Overview

The skill reads odds as advertised, but its setup can execute downloaded software without a clear approval step.

Review and approve CLI installation separately, preferably using a pinned, verified release. OOMOL mediates the connected API account, and requests may consume credits. The remote installer contents and exact system changes remain unverified; no malicious behavior was established.

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
99% confidence
Finding

The supplied command performs remote installer execution, not searching or reading The Odds API data. No connection between this installer and the declared API functionality is established. The downloaded script's contents are not provided, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a live HTTPS response directly into Bash executes mutable remote code without version pinning or independent integrity verification. If the installation endpoint or its publishing infrastructure is compromised, the script could access files and credentials or alter the system with the invoking user's privileges; the PowerShell alternative presents the same underlying risk.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

The fallback setup executes downloaded installer scripts without warning the user about the system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback tells the agent to install software when the CLI is missing, without first requiring user approval or explaining that downloaded code will execute and may modify the local system. Although conditional setup is relevant to the skill, a request to read odds data does not itself authorize software installation; execution remains subject to the host's tool restrictions.

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 82)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