Back to skill

Security audit

Assists in writing high-quality requirements documents using an 8-dimension framework

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for creating and reviewing requirements documents, with no commands, network access, persistence, or sensitive data handling.

This skill is reasonable to install if you want structured help drafting or reviewing PRDs and requirements specs. Be aware that it may activate for product-spec writing or review requests, but its behavior is limited to document guidance and templates.

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
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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The quick-start instruction is broad enough to trigger on generic requests like 'write' or 'review' a document, which can cause the skill to activate outside its narrowly intended context. This is not directly harmful by itself, but over-broad activation increases the chance of inappropriate routing, user confusion, or unintended application of the skill in unrelated workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger says to activate when a user asks to write, draft, review, or structure a requirements document, PRD, or product spec, which is a broad natural-language condition without clear boundaries or exclusion examples. Because these verbs are common in everyday product-work conversations, the skill may be invoked in situations where the user is not explicitly seeking this framework-based requirements skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.