ClawHub
Back to skill

Security audit

prd-autogen-and-review

Security checks for vulnerabilities and agentic risk

Overview

This is a PRD generation and review helper whose optional file output is disclosed and user-directed, with no evidence of hidden execution or credential access.

Installers should treat this as a content-generation skill. Before asking it to export files or JSON for CI, review the PRD for confidential roadmap, customer, security, or business details and choose filenames/locations deliberately.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: "prd-autogen-and-review"
description: "一句话需求 → 结构化 PRD + 评审 Checklist。支持中英文、图表、JSON导出、多角色评审。"
---

# PRD 自动生成 + 需求评审 Skill

## 概述

本 Skill 将用户输入的**一句话需求**（中文或英文），自动展开为结构化的**产品需求文档（PRD）**，并附带一份**需求评审 Checklist**，用于后续评审和验收。

支持三种增强模式：
- **图表模式**：在 PRD 中自动生成 UML 用例图（SVG）
- **导出模式**：输出结构化 JSON 数据，对接 CI/Notion/Jira
- **多角色评审模式**：从 PM/

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger list includes very broad phrases such as generic '需求/requirements' requests, which can cause the skill to activate in conversations that are not actually asking for PRD generation. In an agent setting, over-broad activation can hijack unrelated user workflows, leading to unintended content generation or downstream file/output actions without clear user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill states that it may write PRD and JSON files into the workspace on request, but it does not require an explicit safety notice or confirmation before modifying local files. In agent environments, silent or weakly-signaled file creation can overwrite existing artifacts, leave sensitive requirement data on disk, or surprise users who expected a text-only response.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill mentions that generated JSON can be written for CI use, but it does not warn that PRD content may contain confidential product plans, internal assumptions, or security-related notes that could be exposed to downstream systems. If automatically consumed by CI or integrations, sensitive metadata may be retained, logged, or propagated beyond the original chat context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.