Back to skill

Security audit

App Website Funnel Cloner Expert

Security checks for vulnerabilities and agentic risk

Overview

The skill’s website analysis purpose is coherent, but it fetches and renders user-supplied URLs without clear network safety limits or consent disclosures.

Install only if you are comfortable with the agent retrieving and analyzing URLs you provide. Use it only on public pages you are authorized to analyze, avoid private or sensitive URLs, and run retrieval in a sandbox without unrelated credentials or internal network access.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:73
Finding

Unrestricted User-Controlled URL Retrieval Enables SSRF

Content
View full analysis
[--industry ] [--tone ]", "examples": [ "/funnel-cloner clone-website https://example.com", "/funnel-cloner clone-website \"pasted content\" --industry saas --tone professional" ] } ``` `skill.json:69-77`: ```json { "name": "analyze-only", "description": "Analyze structure without cloning (get blueprint)", "usage": "/funnel-cloner analyze-only [--depth ]", "examples": [ "/funnel-cloner analyze-only https://example.com", "/funnel-cloner analyze-only \"website content\" --depth comprehensive" ] } ``` `skill.json:147-155`: ```json "dependencies": { "system": { "curl": "For fetching website content", "puppeteer": "For JavaScript-rendered website analysis", "html2canvas": "For layout analysis and screenshot generation" }, "api": { "openai": "For content generation", "plagiarism-check": "For originality verification (optional)" } } ``` `skill.json:203-210`: ```json "openclaw": { "requires": { "env": ["OPENAI_API_KEY"], "bins": ["curl", "puppeteer", "html2canvas"] }, "primaryEnv": "OPENAI_API_KEY", "emoji": "🔄", "tier": "expert", ``` ### Technical Analysi ...[truncated 3397 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation keywords are broad enough to trigger on ordinary requests like analysis, redesign, or competitive research, causing the skill to engage in cloning-oriented behavior when the user did not explicitly ask for it. In this context, that increases the chance the agent will fetch third-party sites and provide assistance for imitation of external properties, which can create legal, privacy, and policy risks even if the skill claims to avoid direct copying.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The workflow instructs the agent to fetch webpages and analyze external HTML/CSS/content, but the skill does not clearly warn users up front that third-party URLs will be retrieved and processed. This lack of disclosure can lead to unintended collection and handling of external content, increasing privacy/compliance risk and making it easier to use the skill for unauthorized scraping or analysis of third-party properties.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The keyword trigger pattern is excessively broad and includes generic terms like 'landing page', 'competitive analysis', 'redesign', and 'analyze website', which can cause the skill to activate in unrelated conversations. Because this skill performs cloning-oriented analysis and may fetch external URLs, unintended invocation could lead to unexpected scraping, processing of user-provided content, or generation of outputs that facilitate imitation of third-party sites or funnels.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest advertises use of curl, puppeteer, html2canvas, OpenAI, and a plagiarism-check API to fetch, render, screenshot, and transmit website or pasted content, but it does not clearly disclose these behaviors to the user at runtime. This creates privacy and compliance risk because sensitive URLs, proprietary page content, screenshots, or user-supplied material may be sent to external tools or services without informed consent.

Content

No source excerpt is available for this finding.