ClawHub
Back to skill

Security audit

input classification

Security checks for vulnerabilities and agentic risk

Overview

This documentation-only skill is purpose-aligned for classifying requests, with the main caveat that deployments should review its audit-log retention settings.

Before installing, confirm that the surrounding platform's log retention, access controls, and privacy policy match the documented audit behavior, especially if user requests may reveal sensitive intent. No artifact evidence shows code execution, credential handling, exfiltration, destructive behavior, or hidden persistence.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The logging section mandates broad, long-term retention of classification and audit data, including hashes, category decisions, risk levels, and clarified-input-derived metadata, but does not explicitly require data minimization, redaction, or privacy review for user-derived content. In a system that classifies user requests before task execution, this can lead to unnecessary persistence of sensitive behavioral or contextual data, increasing privacy, compliance, and insider-access risk if logs are over-collected or later correlated.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file includes the example input "Help with this thing," which is a highly generic phrase that overlaps with everyday speech. Although presented as a low-confidence example, the document does not explicitly state that such broad phrasing should not be used as a skill trigger, leaving trigger scope underspecified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.