ClawHub
Back to skill

Security audit

Gemini

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent Gemini connector, but its setup guidance can run an unverified remote installer script if the required CLI is missing.

Review the oo CLI installer source and prefer a verified/manual install path before using this skill. Normal Gemini actions are clearly described, but do not let an agent run the remote installer, authenticate, or connect billing/API credentials unless you intentionally approve those setup steps.

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 use of a remote install command piped directly into a shell (curl ... | bash), which executes unverified code from the network without integrity checking. If the remote script, hosting, TLS trust chain, or distribution path is compromised, an attacker could achieve arbitrary code execution on the host running the skill.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L03 says to use this skill for "ANY Gemini request," including broad activities like reading, creating, and updating data. This scope is so general that it lacks clear trigger boundaries and could overlap with many normal requests involving Gemini, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.