ClawHub
Back to skill

Security audit

Product Owner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a product-owner helper that stores backlog and product context locally, with no executable code or external data transfer found.

Choose the less proactive setup option if you only want help on explicit request, and avoid storing confidential business details in ~/product-owner/ unless local persistence is acceptable for your environment.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Hidden Instructions

High
Category
Prompt Injection
Content
integration: pending

## Product Context
<!-- Product name, description, target users -->
<!-- Business model, key metrics -->

## Team Context
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The setup instructs the skill to ask for broad activation such as helping whenever the user is working on backlogs or user stories and to assist with sprint planning proactively. This can cause the agent to insert itself into many common product-workflow contexts without a narrowly scoped trigger, increasing the chance of overcollection of context, unwanted persistence, or action based on ambiguous user intent.

Static analysis

No suspicious patterns detected.