ClawHub
Back to skill

Security audit

ai-grammar-checker

Security checks for vulnerabilities and agentic risk

Overview

This grammar-checking skill is small and purpose-aligned, but users should know it is vague about when it runs and may send text to an external grammar service.

Before installing, confirm what external grammar service is used and avoid sending secrets, proprietary documents, regulated data, or private text unless that provider is approved. The skill should ideally narrow its use cases to grammar and proofreading only.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
97% confidence
Finding

The skill's usage guidance is overly broad and can cause the agent to invoke it for vague categories like 'nlp related functionality' or 'Ai operations' rather than a clearly scoped grammar-checking task. Overbroad triggers increase the chance that unrelated or sensitive user text is routed into this skill unnecessarily, which is especially risky because the skill appears to rely on an external API.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation tells users to configure an API key for a grammar service but does not warn that submitted text may be transmitted to a third-party provider. This omission can lead to accidental disclosure of sensitive, proprietary, or regulated text, especially if users assume processing is local.

Content

No source excerpt is available for this finding.