ClawHub
Back to skill

Security audit

referrals

Security checks for vulnerabilities and agentic risk

Overview

This skill provides referral and affiliate marketing guidance with no executable code, persistence, credential handling, or hidden data flows.

Installers should understand that the skill may activate for broad referral, affiliate, partner, or word-of-mouth marketing questions. It may read a local product-marketing context file if one exists, but it does not run code or access credentials.

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
94% confidence
Finding

The manifest description says to use this skill whenever the user wants to create, optimize, or analyze several broad marketing concepts and adds 'Use this whenever someone wants existing users or partners to bring in new customers.' This is a wide natural-language trigger without clear exclusion boundaries or negative examples, which increases the chance of unintended invocation during general growth or marketing conversations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The eval explicitly rewards the skill for triggering on vague, casual phrasing without also requiring disambiguation rules or exclusion criteria. In an agent-routing context, this can cause over-broad activation, where loosely related requests are pulled into the referrals skill and receive inappropriate guidance, increasing the chance of wrong task selection or policy bypass through ambiguous prompts.

Content

No source excerpt is available for this finding.