ClawHub
Back to skill

Security audit

OpenAI

Security checks for vulnerabilities and agentic risk

Overview

This OpenAI connector skill is mostly transparent, but it routes very broadly into a credentialed account and includes unsafe remote shell install instructions.

Review this skill before installing if you use OpenAI for paid or sensitive work. Prefer installing the oo CLI through a verified package or reviewed installer, and only let the skill run account-changing OpenAI actions after checking the exact payload, cost impact, and target resource.

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 (3)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill recommends piping a remotely fetched script directly into a shell (curl ... | bash), which is a well-known supply-chain and remote-code-execution risk. If the remote server, network path, or hosted script is compromised, an agent or user following this instruction could execute arbitrary code on the local system with the user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The instruction lacks clear boundaries on when the skill should not activate, so the skill may be selected for a wide range of unrelated or low-risk OpenAI-themed tasks. Because this skill provides operational access through a connector, ambiguous routing is more dangerous here than in a read-only reference skill: mis-selection could lead to credentialed actions or unnecessary schema/connector calls.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The instruction lacks clear boundaries on when the skill should not activate, so the skill may be selected for a wide range of unrelated or low-risk OpenAI-themed tasks. Because this skill provides operational access through a connector, ambiguous routing is more dangerous here than in a read-only reference skill: mis-selection could lead to credentialed actions or unnecessary schema/connector calls.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.