Back to skill

Security audit

结构化头脑风暴

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only brainstorming aid with no executable install behavior, but its mention of automatic knowledge-base archiving is unclear.

Before installing, assume brainstorm content may be saved if the host platform honors the archive claim. Avoid sensitive plans unless you understand the knowledge-base location, retention, access, and deletion controls.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The description states that brainstorm sessions are automatically archived to a knowledge base, but it does not warn users that their inputs may be stored persistently. Because brainstorming often contains sensitive plans, product ideas, or internal constraints, silent persistence creates a meaningful privacy and data-governance risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation phrase "想一下" is a common conversational expression, so the skill may trigger unintentionally during normal user interactions. This can cause unwanted execution of the brainstorming workflow and, in this skill's context, may also lead to accidental collection or archival of user content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

Natural-language policy violations include forcing a specific language without user opt-in. This skill’s description and activation guidance are primarily Chinese, and the file does not state that the skill is region-specific or offer language flexibility, which can amount to an implicit language constraint.

Content

No source excerpt is available for this finding.