ClawHub
Back to skill

Security audit

Conversion Copywriter

Security checks for vulnerabilities and agentic risk

Overview

This is a copywriting guidance skill with no executable code, persistence, credential handling, or hidden data movement.

Safe to install for marketing-copy assistance. Before using generated copy publicly, verify factual claims, testimonials, scarcity, income or health/legal/financial statements, and avoid pasting confidential customer transcripts unless appropriate for your environment.

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 (2)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
## Edge Cases

### Regulated Industries (Finance, Health, Legal)
- No income claims without disclaimers
- "Results may vary" mandatory with testimonials
- Avoid superlatives ("best," "guaranteed results") — use "designed to" language
- Have compliance review BEFORE publishing, not after
Confidence
80% confidence
Finding
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill exposes very broad natural-language triggers such as 'Write a landing page for [product]' and 'Audit this copy: [paste]' without clear activation boundaries, confirmation requirements, or safety exclusions. In an agent setting, this can cause overbroad invocation, unintended processing of arbitrary pasted content, or execution in contexts the user did not explicitly intend, increasing the risk of misuse, prompt injection propagation, or policy-sensitive content generation.