Back to skill

Security audit

社交媒体配图设计 Social Media Design

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill benign because the reported concern is a language-specific confirmation workflow, while no malicious behavior was reported; confidence is medium and inspection was only 50% complete.

The verdict is benign, but confidence is medium and only half of the components were scanned. Before installing, consider whether the required Chinese confirmation suits you, and review the installation details and referenced items yourself because the scan could not fully assess them.

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
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 (2)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md
[English](./SKILL.md) · [中文](./SKILL-cn.md)

The workflow mandates Chinese confirmation prompts and a Chinese approval response without user opt-in.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow explicitly instructs the agent to ask prescribed Chinese questions and requires the user to answer “确认” before generation. This imposes a language-specific interaction without offering a language choice or justifying the restriction.

Content

No source excerpt is available for this finding.