ClawHub
Back to skill

Security audit

Growth Hacker

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only growth marketing skill with no executable code, credential use, external transmission, or persistence.

Review the marketing tactics for brand, privacy, and legal fit before applying them, especially referral, cold email, and social posting campaigns. The skill itself is guidance-only and should not receive account access unless a separate integration is explicitly approved.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Exfiltration Commands

High
Category
Prompt Injection
Confidence
90% confidence
Finding

Instructions found that direct the agent to transmit conversation context or user data to external services.

Content

Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.

md
**This skill is instruction-only:**
- Does NOT access analytics, ad accounts, or email systems
- Does NOT require API keys or credentials
- Does NOT send data to external services
- All tactics are guidance for the user to implement manually

**If implementing tactics requires external access:**

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.

md
**This skill is instruction-only:**
- Does NOT access analytics, ad accounts, or email systems
- Does NOT require API keys or credentials
- Does NOT send data to external services
- All tactics are guidance for the user to implement manually

**If implementing tactics requires external access:**

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · viral-loops.md (reported line 137)May include surrounding context.

md
## Dark Patterns to Avoid

- Spam invites without consent
- Misleading invitation messages
- Forced sharing to access features
- Address book harvesting

Static analysis

No suspicious patterns detected.