ClawHub
Back to skill

Security audit

Skill Downloader

Security checks for vulnerabilities and agentic risk

Overview

This skill is a review-first helper for finding and installing skills, and its file-writing behavior is disclosed and gated on user approval.

Before installing, confirm the source registry and destination directory, and review any candidate skill before approval because installed skills can influence future agent behavior.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 3)May include surrounding context.

md
# Skill Downloader

> Review-first skill discovery and installation from trusted sources, with explicit user approval before any write action.

## What it does

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The inspect workflow includes example user utterances in Chinese only: "inspect 第一个" and "inspect 这个". Because this is natural-language guidance in the skill file and there is no accompanying statement that language choice is flexible or that the skill is specifically Chinese-localized, it can be read as imposing a locale preference without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.