ClawHub
Back to skill

Security audit

UniRateAPI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent UniRateAPI read connector, with a disclosed but risky one-time CLI install command users should treat carefully.

Install only if you are comfortable using OOMOL as the intermediary for UniRateAPI and installing/signing into the oo CLI. Treat the curl/PowerShell install commands as privileged software installation and verify them through official OOMOL sources before running.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs users to install software via a direct network fetch piped into a shell (curl ... | bash), which executes remote code without verification. If the install endpoint, transport, or upstream distribution is compromised, this can lead to arbitrary code execution on the host.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest describes the skill as only for 'searching and reading data', but the operational guidance is generic and allows running any connector action discovered at runtime. If the connector later exposes write or destructive actions, an agent may invoke them under a misleading read-only trust boundary, causing unintended state changes.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill states that untagged actions are reads, but execution is driven by live schema lookup and a generic action runner, which does not enforce read-only behavior. This creates a policy gap where mislabeled or newly added actions could be executed without the intended safeguards.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.