ClawHub
Back to skill

Security audit

High Repeat Small Goods Ops

Security checks for vulnerabilities and agentic risk

Overview

This skill is a domain-specific e-commerce operations advisor with broad activation wording but no hidden code, credential use, persistence, or destructive behavior.

Install this only if you want a specialized workflow for repeat-purchase small-goods e-commerce operations. Be aware it may activate on broad store-operations topics, and some referenced helper files are absent, so template-generation commands may not work as written.

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
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description contains very broad trigger terms covering generic e-commerce topics like store operations, campaigns, reviews, ROI, GMV, and multiple major platforms. This can cause the skill to activate in many ordinary commerce conversations where the user did not request this workflow, increasing the chance of prompt hijacking of task routing, irrelevant instruction injection, or overshadowing more appropriate skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.