ClawHub
Back to skill

Security audit

Prd To Issues

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it advertises: it turns a PRD GitHub issue into reviewed implementation issues, with no hidden scripts or persistence.

Before installing, be aware that using this skill can read GitHub issue contents and create new GitHub issues. Confirm the repository, PRD issue, and drafted issue text before letting the agent run the create step, especially for private or sensitive projects.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill directs the agent to create GitHub issues with `gh issue create`, which performs a write action against an external system, but it provides no explicit warning or confirmation step. Without clear disclosure and approval, the agent could create unwanted tickets, leak sensitive PRD details into GitHub, or modify project workflow in a way the user did not intend.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The skill instructs the agent to fetch a GitHub issue with `gh issue view`, which triggers an external API/network action, but it does not tell the user that repository data may be accessed or transmitted outside the current conversation context. This weakens informed consent and can surprise users in sensitive or private repositories, though the action is read-only and lower risk than write operations.

Static analysis

No suspicious patterns detected.