ClawHub
Back to skill

Security audit

Gumroad Product Page Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed markdown-only Gumroad page copy generator with compliance caveats, but users should avoid publishing regulated financial or health copy without required disclaimers and legal review.

Before installing, treat this as a copy-generation aid, not a compliance system. Do not use disclaimer suppression for public financial, investment, tax, or health product pages, and have regulated claims reviewed before publishing. Also note that the package appears incomplete as shipped because the README references scripts and template data that are not present in the artifact.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
90% confidence
Finding

The README explicitly documents a --no-disclaimer option that disables legal disclaimer injection, which undermines the stated compliance and safety purpose of the tool. In a skill designed to generate sales pages for regulated categories like financial, investment, and health products, making disclaimer removal easy can lead to misleading or non-compliant marketing copy being produced and published.

Content

Scanner excerpt · README.md (reported line 31)May include surrounding context.

md
# Force specific disclaimer type
python3 scripts/generate-page.py product.json --disclaimer-type financial

# Skip disclaimer (draft only)
python3 scripts/generate-page.py product.json --no-disclaimer

# Inline JSON

Vague Triggers

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown/manifest file includes an empty trigger_patterns list, so it does not specify what phrases or conditions should activate the skill. Without explicit trigger scope or exclusions, invocation behavior is ambiguous and may rely on overly broad defaults elsewhere in the system.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.