Back to skill

Security audit

Dealroom

Security checks for vulnerabilities and agentic risk

Overview

The Dealroom searches fit the stated purpose, but setup tells the agent to execute unverified downloaded code without first seeking your approval.

Review and approve the CLI installation separately, using a verified release where possible. Consider its automatic skill synchronization and connect only the Dealroom account you intend to use. The bundled instructions were fully inspected, but the external installers and hosted connector implementation 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
96% confidence
Finding

The supplied chunk performs remote script execution rather than a Dealroom data operation. Although installation can be a supporting implementation detail, this chunk provides no evidence that the Oomol installer supports the declared Dealroom functionality. The downloaded script's contents and resulting effects are not shown.

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 mutable external content without a pinned version, integrity verification, or inspection; the PowerShell example has the same issue. If the installer source or delivery infrastructure is compromised, malicious code could run with the agent process's privileges and access local data or credentials, although the file provides no evidence that the endpoint is currently malicious.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback instructs the agent to install software when the CLI is missing without first explaining that downloaded code will execute locally or requesting approval for system changes. Restricting installation to a missing-CLI error reduces its frequency, but does not authorize modifications to the user's environment.

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 78)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