ClawHub
Back to skill

Security audit

我的技能

Security checks for vulnerabilities and agentic risk

Overview

This is an unfinished skill template with no executable behavior or sensitive access, but it is too underspecified to be useful as published.

Before installing, treat this as an incomplete template rather than a usable skill. Ask the publisher to replace all XXX placeholders with a clear purpose, trigger conditions, inputs, outputs, and supported language expectations.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill's invocation field is left as a placeholder ('调用方式：XXX'), so there is no defined trigger condition or invocation contract. This can cause the agent or integrator to invoke the skill in unintended contexts, increasing the risk of misuse, prompt-routing errors, or unsafe execution paths because the boundaries for when and how the skill should run are undocumented.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

All visible natural-language instructions and headings are written only in Chinese, and the template does not indicate that language selection is optional or limited to a justified region-specific context. This can violate language/locale policy when users are not offered an explicit language choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.