ClawHub
Back to skill

Security audit

Promo Traffic Stress Monitor

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow Markdown guidance skill for live promotion operations, with no executable code, persistence, credential access, or hidden behavior found.

Installers should treat this as an advisory promo-operations aid: provide current metrics deliberately, confirm assumptions like margin and breakeven ROAS, and keep human approval on real ad budget, inventory, or site changes.

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
94% confidence
Finding
The skill description contains many broad natural-language activation cues such as generic mentions of scaling or cutting ads, server strain, stockouts, and poor order conversion. This can cause the skill to trigger outside its intended scope, leading an agent to apply promo-operations guidance in loosely related conversations and potentially produce inappropriate or overconfident business actions.

Static analysis

No suspicious patterns detected.