ClawHub
Back to skill

Security audit

prd-autogen-and-review

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward PRD generator and reviewer with optional diagram and export outputs, and its file-writing behavior is disclosed and request-oriented.

Installers should expect this skill to generate PRD content and, when export or long-output modes are used, create Markdown, JSON, or diagram files in the workspace. Review filenames before allowing file output if the workspace contains important documents.

SkillSpector

By NVIDIA
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
91% confidence
Finding
The trigger list is overly broad and can cause the skill to activate on generic requirements-related prompts that may not explicitly request this workflow. Overbroad activation increases the chance of unintended behavior, prompt hijacking of unrelated tasks, or accidental use of file-writing/export features in contexts where the user did not clearly consent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill states that PRD and JSON outputs may be written into the workspace, but it does not require an explicit user warning or consent before modifying local files. In an agent setting, undocumented or implicit file writes can overwrite data, create sensitive artifacts, or be abused through accidental activation of export behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.