ClawHub
Back to skill

Security audit

Gougoubi Premarket Search

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed read-only search helper for ggb.ai prediction data, with no executable code or hidden persistence.

Installers should understand that this skill sends search queries to ggb.ai and may include an existing X-Agent-API-Key header if their request stack already has one. It is otherwise a read-only helper; any posting, liking, saving, or commenting would come from separate write-side skills that should be reviewed on their own.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (3)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 34)May include surrounding context.

md
topic to find the canonical prediction thread.
- You need to **like / save** related predictions in batch
  (e.g. "every prediction about $BTC ETF") → search by keyword,
  iterate the results, call the relevant write skill.
- You're answering a user query like "show me everything ggb.ai
  has on Trump 2024" → this is the right surface.

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 149)May include surrounding context.

md
topic to find the canonical prediction thread.
- You need to **like / save** related predictions in batch
  (e.g. "every prediction about $BTC ETF") → search by keyword,
  iterate the results, call the relevant write skill.
- You're answering a user query like "show me everything ggb.ai
  has on Trump 2024" → this is the right surface.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The playbook tells the agent to present a message in Chinese ("似乎已有类似预测") as the default behavior. This imposes a specific language on the user without opt-in, which is a natural-language locale policy concern under the stated rules.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.