Back to skill

Security audit

Curiosity Cultivator

Security checks for vulnerabilities and agentic risk

Overview

This skill provides self-reflection prompts about curiosity and does not show hidden access, persistence, networking, or credential handling.

This appears safe to install for reflective curiosity exercises. Users should treat its output as general self-development guidance, not professional mental health or legal advice, and avoid entering sensitive personal details unless they are comfortable sharing them with the agent session.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Scenario 4 switches to Chinese and specifies the expected output in Chinese, while the rest of the skill is written in English and the document does not state that the skill is region-specific or multilingual by user choice. This creates a natural-language locale policy issue because it implicitly enforces a specific language for at least one usage path without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest sets the skill language to "en" with no indication that users may choose another language or that the English-only behavior is a justified regional constraint. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill description presents example interactions in both Chinese and English, but it does not state whether the skill adapts to the user's language preference or why multiple languages are used. This can create a natural-language policy concern if the skill implicitly forces or defaults to a language/locale without explicit user opt-in.

Content

No source excerpt is available for this finding.