ClawHub
Back to skill

Security audit

Essay Writing

Security checks for vulnerabilities and agentic risk

Overview

This is a writing-helper skill with a clearly disclosed local profile step and no executable or hidden installation behavior.

Install this if you want a Chinese op-ed/argumentative-writing assistant. Be aware that it may read a local personal writing profile at ~/.workbuddy/essay_writing_profile.md and incorporate personal experiences into drafts, so keep that file limited to material you are willing to review for publication; the skill does require a privacy approval step before final output.

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 (3)

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 · SKILL.md (reported line 3)May include surrounding context.

md
---
name: essay-writing
description: "Chinese argumentative essay and op-ed writing skill. Produces polished content for Zhihu (知乎), WeChat Official Accounts (公众号), Xiaohongshu (小红书), and Douyin (抖音). This skill should be used when users ask to write argumentative essays, social commentary, opinion pieces, Zhihu answers, public account articles, RED notes, or short-video scripts. Not suitable for pure narrative (fiction/novels), formal academic papers, official documents, press releases, or slide copy."
agent_created: true
---

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description and purpose state that this is a Chinese essay-writing skill and require output aimed at Chinese platforms, but nowhere in the file is there an explicit user opt-in or language-choice mechanism. Because the skill imposes a specific language/locale as a default behavioral constraint in natural language, this matches the policy-violation category.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% 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 · SKILL.md (reported line 138)May include surrounding context.

md
### Layer 1 — Readability: Clear to the educated general reader

The target reader has roughly the literacy of a Chinese university graduate. The
prose must be clear without being simplistic, and sophisticated without pedantry.
The reader should finish thinking "this person pointed out something I hadn't
considered," not "this person is showing off terminology" or "what was the point."

Static analysis

No suspicious patterns detected.