ClawHub
Back to skill

Security audit

Deep Research Gemini

Security checks for vulnerabilities and agentic risk

Overview

The skill has a legitimate research purpose, but its reviewed package does not include the script it tells agents to run for a paid external Gemini workflow.

Review or supply the missing research script and requirements before installing or running this skill. Treat queries and follow-ups as data sent to Google Gemini, avoid sensitive due-diligence material unless that is intended, and monitor API costs.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The description advertises autonomous multi-step research across broad domains without stating any trigger constraints, approval requirements, or bounded scope. This can cause over-invocation of a powerful external research capability, increasing the chance of unintended data sharing, excessive autonomy, or misuse in sensitive due-diligence and technical research contexts.

Static analysis

No suspicious patterns detected.