ClawHub
Back to skill

Security audit

PRD for AI Agents

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Markdown-only PRD-writing helper that asks clarifying questions and creates planning documents, with no hidden code execution or credential access found.

Use this when you want a structured PRD or build plan for an AI coding agent. Expect it to ask discovery questions and write Markdown planning files; review any generated CLAUDE.md or AGENTS.md before letting other agents rely on them.

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
94% confidence
Finding

The trigger description includes generic phrases such as "spec a feature," "create a build plan," and activating when a user shares a "raw idea dump" and wants something an agent can build from. These conditions are broad enough to overlap with common planning or brainstorming requests, and the file does not provide explicit exclusion examples in the trigger block to sharply distinguish when this skill should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.