Back to skill

Security audit

IdeaForge

Security checks for vulnerabilities and agentic risk

Overview

This skill is a planning assistant for turning vague product ideas into implementation plans, with no hidden code execution, persistence, or sensitive data access.

Install this if you want a Chinese-language workflow for scoping product or coding ideas into a detailed implementation plan. Be aware it may trigger on broad brainstorming phrases, and it may proactively recommend technical choices and search for references when planning.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file is entirely written as Chinese-language operational guidance and presents the skill behavior in Chinese without any indication that the user can choose another language. Under the policy, a fixed language or locale without opt-in is a natural-language policy concern unless it is explicitly justified as region-specific.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are broad enough to match many normal user requests such as 'help me make a tool' or 'I have an idea', which can cause the skill to activate outside its intended scope. Over-broad activation increases prompt-surface exposure and may hijack unrelated conversations, causing the agent to follow this skill's workflow when another behavior would be safer or more appropriate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.