Back to skill

Security audit

OpenSEO MCP

Security checks for vulnerabilities and agentic risk

Overview

Review setup carefully: it automatically executes downloaded software without explaining that the dependency can also install other agent skills.

Review and install the CLI separately before allowing agent use, and check whether its automatic installation of other agent skills is acceptable. Disable that synchronization if unwanted. Connect only the intended OpenSEO account and retain approval for changes, deletion, and sharing. The remote installer contents remain unverified; no malicious intent 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 code installs software from a different service and contains no OpenSEO MCP operations. Nothing supplied establishes this installer as a necessary supporting implementation detail for OpenSEO. The remote script's contents are not provided, so its further behavior cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping the HTTPS installer directly into bash executes mutable remote content without verifying its provenance or integrity. HTTPS protects transport but cannot prevent a compromised publisher or distribution endpoint from serving malicious code that could access local files and credentials; this is the same underlying installation risk identified by SQP-2, not a separate exploit.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

First-time setup executes downloaded installation scripts without a system-integrity warning.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The setup instructions direct the agent to execute downloaded shell or PowerShell scripts without inspection, integrity verification, or explicit installation approval. If the distribution endpoint or its delivery pipeline is compromised, the script can execute arbitrary code with the agent's local privileges; restricting setup to a missing-CLI error reduces exposure but does not remove this risk.

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 77)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