ClawHub
Back to skill

Security audit

Creator Outreach Sequence Lab

Security checks for vulnerabilities and agentic risk

Overview

This is a plain text outreach-planning skill with no code execution, persistence, credential access, or hidden behavior.

Before installing, use this skill only for compliant, targeted creator outreach where recipients and platform rules are appropriate. Review generated messages for consent, truthful claims, opt-out handling, and anti-spam compliance before using them.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The invocation description is broad enough to trigger on common requests like improving reply rates or scaling outreach, without clearly limiting when this skill should or should not activate. Overbroad activation can cause the agent to apply persuasive outreach-generation behavior in unintended contexts, increasing the chance of spam-oriented, non-compliant, or contextually inappropriate assistance.

Static analysis

No suspicious patterns detected.