Back to skill

Security audit

AI Lead Generation & Prospect Finder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed B2B prospecting template generator with no executable code, scraping, persistence, or credential handling.

Installers should understand that the skill may be triggered broadly for lead-generation-adjacent requests. Provide only business prospecting details you are comfortable using for sales planning, and independently verify contact information and compliance with privacy laws and platform terms before outreach.

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
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)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill metadata description contains very broad auto-trigger language such as activating for anything related to lead generation or even casually phrased requests. This can cause the skill to be invoked outside the user's true intent, leading to irrelevant execution, over-collection of user/business data, or steering conversations into prospecting workflows when not explicitly requested.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The dedicated trigger section explicitly instructs immediate activation on a wide set of broad phrases without guardrails, negative examples, or ambiguity handling. In context, this increases the chance of accidental invocation during ordinary sales, marketing, CRM, or research conversations, which may misroute user requests and prompt unnecessary handling of targeting or prospecting-related data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.