ClawHub
Back to skill

Security audit

Runpod

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for managing Runpod through OOMOL, but it includes destructive pod controls and an unverified remote installer command that users should review before use.

Install only if you trust OOMOL and are comfortable connecting your Runpod account through it. Before running setup, prefer a verified or pinned installer path instead of directly piping downloaded scripts into a shell. Confirm pod IDs and effects carefully before stop, reset, restart, start, or delete actions.

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
97% confidence
Finding

The skill instructs users to install the CLI via a remote script piped directly into a shell (curl ... | bash), which executes network-fetched code without verification. If the install endpoint, transport, DNS, or hosting account is compromised, an attacker could achieve arbitrary code execution on the host running the skill.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description says to use this skill for ANY Runpod request and instead of calling the API directly, which can cause overly broad auto-selection for loosely related prompts. In an agentic environment, that increases the chance of invoking a capability with write and destructive actions when the user only mentioned Runpod contextually or when a narrower/manual workflow would be safer.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.