Back to skill

Security audit

SecurityTrails

Security checks for vulnerabilities and agentic risk

Overview

The SecurityTrails lookups fit the stated purpose, but setup directs the agent to execute an unverified remote installer without first obtaining approval.

Review the setup before installing. Use a verified CLI release and require approval before any downloaded installer runs. Consider the CLI's documented agent-skill synchronization and whether you want OOMOL to handle your queries and connected credentials. Installer contents and backend behavior remain unverified; the artifact does not establish malicious intent.

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 executes an Oomol-hosted installer, with no visible connection to SecurityTrails. Although dependency installation can be a supporting implementation detail, this chunk provides no evidence that the installer supports the declared purpose. The downloaded script's further behavior cannot be determined from the supplied code.

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 CLI login and contains no SecurityTrails search or data-reading behavior. Authentication could be a supporting implementation detail, but nothing in the supplied code establishes that this login supports SecurityTrails access.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping a live HTTPS response directly into bash executes whatever the installer endpoint supplies, without a pinned artifact or independent integrity verification. Compromise of the distribution endpoint or its supply chain could enable arbitrary code execution, credential theft, or local modification; HTTPS alone does not protect against a compromised publisher.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The setup workflow executes a downloaded installer without warning the user about running remote code locally.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The fallback instructs the agent to execute downloaded shell or PowerShell code without first warning the user or obtaining explicit approval for local software installation. Although legitimate setup is relevant to the integration and only occurs when the CLI is missing, it expands a read-only data task into local code execution with the invoking user's privileges.

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 79)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