ClawHub
Back to skill

Security audit

Case Study Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only case-study writing skill, but its marketing material includes advice that could encourage nondisclosure to clients about AI-assisted work.

Review the client-disclosure issue before installing or selling services with this skill. Use it only with customer-approved quotes, authorized metrics, and human fact-checking, and disclose AI assistance where contracts, professional norms, or client expectations require it.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The marketing copy explicitly encourages selling AI-generated case study packages without client disclosure ('Your clients don't need to know you used a skill'). This promotes deceptive business practices and can create legal, contractual, and reputational risk if customers expect human-authored deliverables or require disclosure of AI assistance. In this marketing context, the issue is more dangerous because it is framed as a repeatable service playbook and monetization tactic, increasing the likelihood of misuse at scale.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly requests identifiable customer contact details and customer quotes as input, but provides no guidance on consent, minimization, or safe handling of personal data. In a marketing case-study context, this creates a real privacy risk because users may submit names, roles, testimonials, and potentially confidential business information without authorization, leading to disclosure or misuse of personal and client data.

Natural-Language Policy Violations

Low
Confidence
77% confidence
Finding
The file presents fixed output formats such as an SEO blog post in English and does not offer any language or locale choice. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy issue when no region-specific justification is provided.

Static analysis

No suspicious patterns detected.