ClawHub
Back to skill

Security audit

AI Lead Intelligence Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward lead-research helper that uses a disclosed external backend, with no hidden persistence, privilege escalation, or unrelated behavior found.

Before installing, be aware that lead inputs such as company and target persona, plus any API key you provide, are sent to the skill publisher's external backend. Avoid entering confidential prospect notes or sensitive credentials unless you trust that backend and its data practices.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
[One punchy cold email or DM opener tailored to persona]
---

## Output Guidelines
- Be specific, not generic
- Prioritize sales relevance
- Keep each section concise and scannable
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to send user-supplied company/persona data and an access token to a third-party backend, but it provides no user-facing disclosure, consent step, or data-handling constraints. This creates a real privacy and credential-handling risk because users may not realize their inputs and token are being transmitted off-platform to an external service.

External Transmission

Medium
Category
Data Exfiltration
Content
"company": "HubSpot",
    "persona": "Head of Sales"
}
r = requests.post(f"{BASE_URL}/analyze-lead", json=payload, headers=headers)
data = r.json()

print("Status:", r.status_code)
Confidence
80% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
This code sends data to a remote service using a custom access-token header and a JSON payload, but the file provides no warning about transmitting user or system data beyond generic test labels. For code files, network calls that transmit data should have some visible disclosure such as a comment, docstring, or user-facing notice unless the transmission is clearly explained as part of the skill's purpose.

Static analysis

No suspicious patterns detected.