Back to skill

Security audit

domain-navigator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a learning coach that creates a user-controlled Markdown domain map, with no hidden execution, credential use, or background persistence found.

Before installing, note that the skill is designed to keep learning state in a Markdown map and may write that map to a path you provide or confirm. Review the map before pasting it into another AI, because it may contain your goals, background, and learning notes.

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 (2)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

Line L012 states "默认中文,遵循用户语言" (default Chinese, follow the user's language). This sets a specific default language before any user choice, which can conflict with a policy requiring language or locale selection to be user-driven unless clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The natural-language instructions tell users to paste the map into 'any AI' to continue, but the provided prompt text and workflow are entirely Chinese-language with no opt-in or alternative locale guidance. This can be read as enforcing a specific language/locale experience by default, which matches the policy concern for language or locale constraints without user choice.

Content

No source excerpt is available for this finding.