ClawHub
Back to skill

Security audit

OpenRouter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clear OpenRouter connector wrapper, with some setup and account-action cautions but no evidence of hidden or malicious behavior.

Install only if you intend to use OOMOL as an intermediary for your OpenRouter account. Before first-time setup, verify the oo CLI installer source, and confirm any action that could spend credits, create charges, or change account-related data.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill recommends installing the CLI via a remote script piped directly into a shell (curl ... | bash), which executes code fetched at runtime without independent verification. If the install endpoint, transport, or upstream distribution path is compromised, the user could execute arbitrary attacker-controlled code on their system.

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger text is extremely broad: it directs the agent to use this skill for ANY OpenRouter-related request, including reads, creates, and updates, instead of more narrowly scoped actions. That increases the chance of unintended invocation and can route sensitive or state-changing tasks through this skill without sufficient task-specific guardrails or user confirmation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.