ClawHub
Back to skill

Security audit

Product Management OS

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed product-management methodology skill with broad but purpose-aligned guidance and no code, hidden execution, credential access, or persistence.

Install this if you want the agent to apply a structured PM methodology across strategy, discovery, prioritization, specs, launches, and metrics. Be aware that its broad activation wording may make it show up in general product conversations, so use explicit prompts when you do or do not want this framework applied.

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
Confidence
94% confidence
Finding
The README advertises a very broad natural-language invocation, "Help me create a product strategy for our new feature," which overlaps with ordinary conversation and could cause the skill to activate unintentionally in unrelated contexts. Because this is a general product-management skill intended for frequent use, accidental triggering could steer agent behavior, override user intent, or inject methodology when the user did not explicitly request this skill.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The description says to use the skill when 'building products, running discovery, prioritizing features, writing specs, planning launches, or measuring outcomes,' which are very broad activities common to many work conversations. It does not provide exclusion conditions or narrow contextual constraints, so the trigger scope may overlap with ordinary product-related requests and cause unintended invocation.

Static analysis

No suspicious patterns detected.