ClawHub
Back to skill

Security audit

Write A Prd

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple PRD-writing workflow that reads the repository for context and can create a GitHub issue, with no hidden code or persistence beyond the issue it asks to submit.

Install this if you want an agent to help turn feature ideas into PRDs and GitHub issues. Before using it on sensitive or private repositories, confirm where the GitHub issue will be created and review the PRD content before posting.

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 skill’s activation criteria are broad enough to trigger on generic planning or documentation requests, which can cause the agent to enter a repo-exploration and GitHub-issue submission workflow without sufficiently explicit user intent. In this context, the skill also directs aggressive interviewing and repository inspection, so misfires could lead to unnecessary exposure of codebase context or unintended external actions such as filing issues.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.