ClawHub
Back to skill

Security audit

Referral Program

Security checks for vulnerabilities and agentic risk

Overview

This is a marketing guidance skill for referral and affiliate programs, with only scoped context-file reading and no hidden execution, persistence, or data exfiltration behavior.

This skill is safe to install for marketing strategy support. Be aware it may be invoked for some general growth or affiliate conversations, so users should clarify when they want broader launch, email, analytics, or marketing strategy help instead.

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
93% confidence
Finding

The description says to use this skill whenever the user wants to create, optimize, or analyze a referral program and then adds a long list of broad phrases such as 'word of mouth' and 'how to get referrals.' This creates an expansive trigger surface that could overlap with general marketing conversations, without clear exclusion criteria or negative examples to distinguish when another growth or marketing skill should be used instead.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The eval explicitly rewards the skill for triggering on casual phrasing like 'should we do referral or affiliate?', which broadens activation without defining clearer boundaries for when this skill should defer to adjacent skills. In an agent setting, overly broad activation can cause misrouting, leading the system to apply the wrong workflow, miss necessary context checks, or bypass more specialized guidance for affiliate, launch, or email-related requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.