ClawHub
Back to skill

Security audit

customer-acquisition-automation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed public-lead collection and outreach-drafting workflow with explicit human approval before anything is posted.

Before installing, be clear about the product, target audience, allowed platforms, and volume limits. Review every generated draft before sending, use only official platform APIs if publishing, and keep API credentials in environment variables rather than in the skill files.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The invocation phrase "run today's acquisition pipeline" is broad and can trigger a multi-step lead collection and outreach-drafting workflow without clearly constraining targets, channels, rate limits, or compliance checks. In a growth/outreach skill, ambiguous triggers increase the chance the agent collects and prepares spammy, policy-violating, or reputationally harmful outreach based on insufficient user scoping.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation phrases are broad enough that ordinary user requests like 'draft outreach' or 'collect promo leads' could trigger this skill in contexts where the user did not clearly intend customer-acquisition behavior. Because the skill performs collection and generation of outreach content, ambiguous invocation increases the chance of unintended scraping-like activity, unwanted marketing draft generation, or inappropriate task routing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.