ClawHub
Back to skill

Security audit

Olive Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a transparent persona/style skill made of Markdown references, with no executable code or hidden privileged behavior found.

Install this only if you want an agent to adopt this persona's evidence-heavy decision style and Chinese-first communication preference. Review the persona references first, especially if you need responses to remain in another language or avoid third-party persona framing.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README states '中文为主，保留常用 English technical terms' as the default expression style, which can cause the skill to respond in Chinese even when the user did not request that language. This is a genuine safety/usability issue because it can reduce user comprehension, obscure important warnings, and create consent/accessibility problems, though it is not directly a code-execution or data-security flaw.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 330)May include surrounding context.

bash
# 当前项目
mkdir -p .claude/skills
git clone https://github.com/Iamliuxiaozhen/OliveSkill .claude/skills/oliveskill

# 全局安装

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 330)May include surrounding context.

bash
# 当前项目
mkdir -p .claude/skills
git clone https://github.com/Iamliuxiaozhen/OliveSkill .claude/skills/oliveskill

# 全局安装

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly requires primary communication in Chinese without checking user preference, task context, or accessibility needs. This can override user intent, reduce comprehension, and create safety or usability issues when the user expects another language, especially for security, operational, or legal guidance where precision matters.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.