Back to skill

Security audit

Content Brainstorm 自媒体选题策划

Security checks for vulnerabilities and agentic risk

Overview

This is a simple content-planning prompt skill; it is China-platform oriented and has broad activation phrases, but it does not install code or request sensitive access.

Install this if you want a Chinese/social-platform content calendar assistant. Be aware it may activate on broad brainstorming requests, and only provide past performance data or account examples when you intend the assistant to use them for content 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
86% confidence
Finding

The title and description present the skill as generating content calendars for Chinese social media platforms, and the workflow/output guidance continues that assumption without offering the user a language or locale option. This can violate language/locale policy when a skill forces a specific regional context without explicit opt-in or documented justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation triggers include broad, common phrases such as 'brainstorm' and 'what to write', which can cause the skill to activate outside its intended context. In an agent environment, overbroad activation can lead to unintended tool use, irrelevant interception of user requests, and surprise execution of the skill's research workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.