ClawHub
Back to skill

Security audit

PRD Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-oriented PRD drafting and review skill with no executable code, persistence, credential handling, or hidden external actions.

Install this if you want help drafting or reviewing PRDs, especially in Chinese. If you need English or another locale, tell the agent the desired language explicitly before using the skill.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description says to use the skill when 'drafting, improving, reviewing, or explaining' a wide range of product documents, which is a very broad invocation scope rather than a narrowly defined trigger. Although some examples are specific, the overall activation condition is ambiguous enough that ordinary requests about specs or user stories could invoke the skill without clear boundaries or exclusions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The template is entirely written in Chinese and presented as the default PRD standard template, which can steer the agent to produce output in a specific language/locale without explicit user preference. In a drafting skill, this can cause unintended language switching, mismatched stakeholder deliverables, and reduced usability for users expecting another locale, especially if the skill is auto-triggered on broad PRD-related requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown guidance is written as a normative UX specification in Chinese and instructs the PRD generator to follow it when describing interface behavior and copy. Because it does not state that Chinese is optional, user-selected, or limited to a China-specific product context, it effectively forces a specific language/locale without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

Line L004 contains a normative instruction for Claude, and the surrounding skill content is written in Chinese. There is no indication that the user can choose another language or that the Chinese-only behavior is limited to a justified locale-specific context, which may violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The prompt and expected behavior are written entirely in Chinese and implicitly require Chinese output, but the file does not indicate that Chinese is optional or that the skill is intentionally limited to a Chinese-language context. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.