Back to skill

Security audit

requirement-analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese product-requirement analysis template with no executable code, persistence, data access, or hidden behavior.

Install this if you want a Chinese-language assistant for structuring product requirement notes. Be aware it may activate on broad business-background or feature-idea discussions and will default to Chinese output unless the agent or user overrides that preference.

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

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill declares overly broad trigger conditions, including common phrases and even activation when the user does not explicitly ask for requirement analysis. This can cause unintended invocation on unrelated business conversations, leading the agent to over-collect context, produce misleading structured outputs, or interfere with user intent and other safer/more appropriate skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill forces Chinese output by default without checking the user's language preference or obtaining consent. In multilingual environments this can degrade transparency, cause misunderstanding of requirements or acceptance criteria, and create integrity issues if users rely on a document they cannot accurately review.

Content

No source excerpt is available for this finding.