Back to skill

Security audit

DealMachine

Security checks for vulnerabilities and agentic risk

Overview

The DealMachine features fit their stated purpose, but setup can automatically run unverified installer code with broader effects on your agent environment.

Review and install a verified CLI release yourself before use, rather than allowing automatic installer execution. Consider disabling managed skill synchronization if you only want this DealMachine integration. OOMOL mediates your connected-account access, and searches or enrichment may consume credits. The complete bundled artifact was inspected, but the remote installers and hosted connector implementation 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
  • 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
98% confidence
Finding

The supplied command executes an Oomol-hosted installer rather than searching or reading DealMachine data. Nothing in the supplied code establishes this installation as a supporting dependency for the declared functionality. The remote script's contents and any further effects are not visible.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely fetched script directly into Bash executes whatever the endpoint returns with the invoking user's privileges, without a pinned version or independent integrity check. A compromised distribution endpoint could therefore execute arbitrary code and access local data; the PowerShell alternative has the same weakness. The legitimate dependency-installation context and missing-CLI condition limit exposure but do not establish script integrity.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Fallback setup executes downloaded installation scripts without a system-integrity warning or approval step.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The missing-CLI fallback directs the agent to execute an installer without first obtaining approval for local system changes or explaining that remote code will run. Restricting this to a command-not-found error reduces exposure, but a DealMachine data request does not itself authorize software installation.

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 81)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