Back to skill

Security audit

Creative Thought Partner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local creative brainstorming guide that may save the session transcript, but its behavior is coherent with its stated purpose and shows no hidden execution, exfiltration, or privilege escalation.

Before installing, understand that this skill is designed to guide a probing creative conversation and then save a session file that can include the full transcript. Avoid using it for confidential business plans, private personal reflections, or sensitive drafts unless you are comfortable with that local saved record, or ask the agent not to export the 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description is broad enough to match many ordinary brainstorming or writing requests, increasing the chance it will be invoked when the user did not explicitly ask for this behavior. Because the skill steers the conversation in a strong, prescriptive way and later exports session content, over-broad triggering can unexpectedly collect and persist sensitive user ideas or personal context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill specifies that generated output will be saved to a session file, but it never clearly warns the user that their conversation may be persisted. In a conversational ideation context, users may share proprietary concepts, drafts, business strategies, or personal reflections, so silent transcript export creates a meaningful confidentiality and privacy risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.