ClawHub
Back to skill

Security audit

PM Copilot

Security checks for vulnerabilities and agentic risk

Overview

This is a plain product-management assistant skill with broad PM routing guidance but no executable code, persistence, or hidden authority.

Installers should treat this as a general PM helper: useful for vague product tasks, but broad enough that users may want to choose a more specific PM skill when they already know the exact output they need.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation guidance uses generic phrases like '帮我推进这个需求', '你觉得下一步怎么做', and '帮我把这个产品任务做完' as examples for when to use this skill. These overlap with common conversational requests and the file does not provide exclusion criteria or negative examples, increasing the risk of unintended routing to this skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

All listed example user utterances are in Chinese, and the file does not state that language choice is optional or user-driven. This can create a locale/language policy issue because the skill appears tailored to a specific language without offering opt-in or alternatives.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.