ClawHub
Back to skill

Security audit

ooutreachskill

Security checks for vulnerabilities and agentic risk

Overview

This is a mostly transparent outreach-writing skill, but its activation scope is overly broad for a tool that can steer external sales messages and CRM workflows.

Install only if you want Floods-specific outreach templates to appear in sales-message and prospecting workflows. Keep sending messages, publishing personalized pages, and CRM updates under explicit human approval, and be cautious because the trigger wording may cause the skill to affect unrelated DMs or follow-ups.

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

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger instructions are extremely broad and directive ('always trigger') across common terms like DM, outreach, follow-up, prospect, and LinkedIn message. This can cause the skill to activate in many unrelated contexts, increasing the chance that outreach-specific persuasive templates and external-research workflows are injected when the user did not intend it, which can lead to scope hijacking, irrelevant execution, or unsafe handling of contact-generation tasks.

Content

No source excerpt is available for this finding.