ClawHub
Back to skill

Security audit

gtrk 美食解说

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a coherent food-video workflow with disclosed cloud processing and approval before paid actions.

Expect Chinese narration and cloud processing of your selected media. Check media privacy, usage rights, and estimated charges before approving paid steps. The external CLI and companion skills were not included in this artifact review.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The skill requires Chinese-language output without offering a language choice or obtaining user opt-in.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The skill defines its output as a Chinese-language food narration project, a requirement also repeated in the description at L003. It provides no language-selection step or justification for restricting this general food-video workflow to Chinese.

Content

No source excerpt is available for this finding.