ClawHub
Back to skill

Security audit

Comeback Buddy

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese comeback-writing skill with disclosed harsh examples, but it has no code, hidden access, persistence, or credential handling.

Install only if you want a Chinese-language assistant for drafting firm or sharp replies. Review aggressive outputs before sending them, especially in workplace, family, or relationship contexts where escalation could have real consequences.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are broad enough to match many ordinary requests about replying to messages or analyzing conversations, which can cause the skill to activate outside a narrowly intended scope. In this skill, that matters because it is designed to generate escalating comeback content, including aggressive and 'nuclear' options, so accidental invocation could steer benign interactions toward conflict escalation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file provides escalating 'nuclear' workplace confrontation scripts, including insulting, demeaning, and retaliatory language, while normalizing severe interpersonal escalation as a ready-to-use output. Although it includes a brief warning, the skill context explicitly targets users who want comeback lines and even 'leave-the-job level' options, which increases the likelihood of real-world harm such as workplace retaliation, HR complaints, relationship damage, or escalation of harassment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file title and all instructional content are written in Chinese, and nowhere in the document does it offer an alternative language or indicate that Chinese is a required regional/compliance constraint. Under the policy, natural-language content that effectively forces a language without user opt-in should be flagged.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The guideline "默认中文回复，除非用户用英文提问" forces a default language choice rather than offering the user a language preference. That can violate language/locale policy expectations when no explicit opt-in or documented region-specific justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

All user-facing content and example scripts are written exclusively in Chinese, with no indication that another language can be chosen. Under the stated policy, a skill that imposes a specific language without opt-in can constitute a natural-language policy violation unless the locale restriction is documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.