ClawHub
Back to skill

Security audit

Language Practice Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a simple language-practice guidance skill with no executable code, persistence, credential handling, or hidden high-impact behavior.

Installers should treat this as a low-risk language-learning template skill. Users may want clearer trigger examples if they only want it invoked for vocabulary, grammar, speaking practice, or study planning, but the artifact does not request dangerous access.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation guidance uses generic phrases like 'structured guidance' and 'repeatable prompts the agent can follow' without clearly limiting invocation to specific language-practice tasks. Because there are no negative examples or explicit trigger constraints, the skill could be invoked for many ordinary planning or drafting requests unrelated to its intended scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.