ClawHub
Back to skill

Security audit

Skill Namer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a naming assistant with small helper scripts; its behavior is coherent and low risk, with only minor disclosure notes around remembered preferences and broad activation scope.

Before installing, be aware that the skill may remember your naming preferences for later sessions. Avoid giving API keys unless you explicitly choose API-based availability checking; the default manual mode only produces search links.

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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to remember user preferences for future sessions without requiring explicit user consent or a privacy notice. That can lead to unauthorized persistence of user data and surprise retention of behavioral preferences across sessions, which is especially risky in shared, multi-tenant, or compliance-sensitive environments.

Vague Triggers

Low
Confidence
86% confidence
Finding
In a markdown skill file, trigger scope should be specific enough to avoid accidental activation. The description and opening text broadly say the skill generates names for skills, domains, primitives, and general agent power, but do not define concrete trigger phrases, activation conditions, or exclusions, making the invocation boundary ambiguous.

Static analysis

No suspicious patterns detected.