Back to skill

Security audit

界面设计 · UI Design

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rated this skill suspicious because it flags guidance to bypass protected download filtering, creating a risk around requests to internal services and unvalidated downloads.

Review the skill’s download guidance before installing. Consider whether you are comfortable with instructions that may bypass protected download filtering; scanner coverage is partial, so the results do not establish that all referenced material was assessed.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

Frames security filtering as a reliability problem to justify downloading assets through a less-restricted shell path.

Medium
Category
Prompt Injection
Confidence
96% confidence
Finding

The skill explicitly presents content-type and SSRF filtering as reliability problems and directs the agent to use shell downloads instead, bypassing application-level protections where the shell has broader network access. Remote assets are legitimate for UI work, but automatically following redirects without validating every destination can enable requests to internal services, while accepting arbitrary binary responses increases the risk of importing unsafe content. The HTTPS preference and advice to avoid internal hosts reduce risk but do not enforce these boundaries.

Content

No source excerpt is available for this finding.

The fallback workflow requires a Chinese-language setup prompt without user language opt-in.

Low
Category
Output Handling
Confidence
95% confidence
Finding

The skill instructs the agent to give the user a fixed Chinese-language prompt when a sibling skill is missing or CloudBase capabilities are needed. It offers no language choice and provides no documented regional requirement that justifies imposing Chinese regardless of the user's language.

Content

No source excerpt is available for this finding.