Back to skill

Security audit

Software Concept Architect · Design — Turn Requirements into Clear Concepts

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-oriented design skill that guides a user-confirmed concept design workflow without executable or hidden behavior.

Installers should understand that this skill will guide the agent through structured software concept design and may ask to inspect relevant project facts or write design documentation after confirmation. It does not add executable code or background behavior.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest sets language: en, which indicates the skill is constrained to English. The file does not offer an explicit language/locale choice or user opt-in, so this is a natural-language policy concern under the locale-policy rule.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.