ClawHub
Back to skill

Security audit

Phy Prd Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent PRD-writing assistant with some user-control caveats around broad activation and optional save/commit follow-up actions.

Use this skill when you intentionally want a guided PRD workflow. Prefer explicit invocations like /prd or 'write a PRD', and review any proposed save path, git commit, agent handoff, or local transcript search before allowing it to proceed.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrases include very broad terms like 'new feature' and 'product requirements', which can cause the skill to activate in situations where the user did not explicitly request PRD generation. In a multi-skill or agentic environment, unintended invocation can steer the conversation, collect unnecessary project details, or cascade into later actions such as file-saving or task orchestration that the user did not mean to start.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs the agent to save the generated PRD and create a git commit as part of the workflow, but it does not require an explicit user confirmation or a clear warning that these actions modify the local workspace and repository history. In an agent environment, this can lead to unauthorized file creation and commits, especially if the skill was triggered accidentally or the user only wanted drafting assistance rather than repository changes.

Static analysis

No suspicious patterns detected.