Back to skill

Security audit

SERPHouse

Security checks for vulnerabilities and agentic risk

Overview

The SERPHouse integration is coherent, but its setup can execute changing remote installers without clear user approval or verification.

Review and install the CLI yourself before use, and require approval for installer execution or additional agent-skill changes. OOMOL handles the connected SERPHouse credentials, and searches may consume credits. The concern is uncontrolled setup execution; the artifact does not show exfiltration or destructive intent. Installer contents and backend behavior remain unverified.

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 supplied code performs remote software installation, not SERPHouse searching or data retrieval. No connection between the Oomol installer and the declared SERPHouse functionality is shown, so this cannot be established as a supporting implementation detail. The downloaded script's contents and further effects are not available for assessment.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied chunk performs only a login operation, not SERPHouse searching or data retrieval. Authentication could be a supporting implementation detail, but nothing in the supplied content identifies oo as a SERPHouse client or connects this login to the declared service.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a mutable remote script directly into Bash executes its contents with the agent process's local permissions, without version pinning or independent integrity verification. HTTPS protects transport but does not prevent a compromised distribution endpoint or release pipeline from supplying code that steals accessible secrets or modifies local files; the PowerShell installer has the same underlying risk.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

The setup workflow executes downloaded installer scripts without warning the user about local code execution and system changes.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

A missing CLI triggers instructions to execute a remote installer without first obtaining approval for local software installation and its system changes. Although this is a legitimate dependency setup step, a request to read SERPHouse data does not inherently authorize arbitrary installer execution on the user's machine.

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 80)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