ClawHub
Back to skill

Security audit

Explain

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill adapts explanation style and stores confirmed explanation preferences locally, with no evidence of hidden execution or unsafe behavior.

Before installing, be aware that confirmed explanation preferences may be saved in ~/explain/memory.md. Review or delete that file if you do not want preference history retained on the machine.

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
96% confidence
Finding

The skill explicitly persists user preferences to ~/explain/memory.md but does not disclose this storage behavior to the user or require consent before writing to disk. Even if the data seems low sensitivity, preference histories can reveal interests, domains, and behavioral patterns, creating privacy and retention risk, especially on shared systems or where logs/backups exist.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The description says the skill 'Learns how to explain things to your human' and 'Adapts format, depth, and style by topic,' but it does not define clear trigger phrases, activation boundaries, or situations where it should not activate. In a markdown skill file, this kind of broad, general-purpose phrasing can overlap with many ordinary explanation requests and makes the trigger scope ambiguous.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.