ClawHub
Back to skill

Security audit

Product Requirements Drafter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a PRD-writing assistant with disclosed, document-focused behavior and no evidence of hidden execution, data exfiltration, or persistence.

Before installing, users should know this skill is intended for drafting PRDs and may process confidential roadmap, metric, or customer details that they paste into the chat. The artifact itself instructs the agent not to publish that information externally.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
| Open Questions | Each question has a named decision owner |
| Assumptions | All `[Assumed: ...]` flags are visible and easy to find |

If any check fails, fix it before delivering the PRD. Do not ask the user to fix rubric failures themselves.

---
Confidence
80% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.