ClawHub
Back to skill

Security audit

Spellcheck

Security checks for vulnerabilities and agentic risk

Overview

This spell-checking skill is a disclosed input normalizer with no executable code, network access, credential use, or persistence behavior.

Installers should understand that this skill may quietly normalize obvious prose typos before the agent reasons about a request. It is suitable for general assistance, but exact strings such as code, commands, secrets, file names, URLs, and identifiers should still be treated carefully and preserved as written.

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 default prompt instructs the agent to always route requests through "$spell-checker" before acting, which is an overly broad activation condition. This can cause the skill to intercept unrelated or security-sensitive inputs, increasing the chance of prompt manipulation, unintended transformations, or interference with tasks where preserving original content is important.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.