ClawHub
Back to skill

Security audit

prd-development

Security checks for vulnerabilities and agentic risk

Overview

This skill is a structured PRD-writing workflow with no executable code, persistence, credential access, or hidden data handling.

Install this if you want an agent to follow a fairly opinionated PRD-writing workflow. Be aware that it may activate for broad product-requirement, user-story, feature-description, or meeting-note prompts, and it may suggest loading related domain skills when DNS or botnet/security keywords appear.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill advertises activation on very broad terms like '写PRD', '产品需求文档', '用户故事', '功能说明', and even generic meeting notes or feature descriptions. This can cause the skill to trigger in many ordinary writing contexts, increasing the chance it hijacks unrelated conversations, steers the agent into unnecessary workflow steps, or loads additional domain skills based on weak keyword matching.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.