ClawHub
Back to skill

Security audit

Live Q&A Scripts

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only skill for drafting live-selling Q&A scripts, with no evidence of hidden execution, persistence, credential use, or agent memory manipulation.

This skill appears safe to install for preparing live commerce scripts. Users should still provide only product and policy details they are comfortable using in sales copy, and should verify any claims, guarantees, prices, promotions, shipping terms, and regulated-category wording before going live.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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)

Memory Manipulation

High
Category
Memory Poisoning
Content
## Multi-Host Handoffs

- Use a clear handoff line so the stream doesn't go quiet.
- The incoming host restates the offer and code to reset context.
- Keep a shared cue card so answers stay consistent between hosts.

## Compliance On Air
Confidence
80% confidence
Finding
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Static analysis

No suspicious patterns detected.