Back to skill

Security audit

测试审核记录保存4

Security checks for vulnerabilities and agentic risk

Overview

This brainstorming skill is mostly coherent, but it broadly auto-triggers and tells the agent to write and git-commit design documents without a clear final approval step.

Install only if you want a brainstorming workflow that may activate broadly during design or feature work. Before letting it run, require the agent to ask before writing files or creating git commits, and confirm whether responses should follow your preferred language.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description says it must be used before essentially any creative or behavior-changing work, making the trigger scope extremely broad. In an agent system, such broad applicability can cause unintended invocation, expanding the skill’s authority and increasing the chance that downstream file inspection, document creation, or workflow control occurs without the user explicitly requesting this skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

整个技能说明以中文编写并在描述中使用强制性措辞,但未表明用户可选择其他语言,也没有说明这是特定地区或合规场景所必需。根据语言/区域政策,这构成未经用户选择即强制特定语言的自然语言策略问题。

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to write a design document to docs/plans and commit it to git, but it does not require prior user consent at the point of action. Any capability that persists files or changes repository history is security-relevant because it can modify project state, create misleading artifacts, or commit sensitive/generated content without an explicit approval boundary.

Content

No source excerpt is available for this finding.