Back to skill

Security audit

Red Alarm

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Chinese content-review skill that gives policy-style advice and does not request execution, credentials, persistence, or platform control.

Before installing, understand that this skill will frame matching requests as Xiaohongshu AI-content compliance reviews and will output in Chinese. It is suitable for advisory review of content you provide, but users should not treat its deletion, ban, or reporting recommendations as platform-enforced actions or legal advice.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad, natural-language requests such as '帮我审查这段内容' and '这段内容能发吗', which overlap with common user intents and can cause the skill to activate when the user did not specifically intend to invoke this compliance-review workflow. In an agent environment, unintended activation can lead to context hijacking, misrouting of user requests, or excessive exposure of user content to an over-privileged skill, especially because the skill is designed to inspect arbitrary user-provided text for policy issues.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is extremely broad and includes common phrases like '帮我审查这段内容' and '帮我看看这个内容有没有问题', which can match many ordinary editing, quality-review, or general advice requests. This creates a prompt-routing vulnerability where the skill may activate outside its intended scope, causing incorrect policy framing and over-collection of user context for unrelated tasks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill hard-codes '全文使用中文', overriding normal user language preference and potentially conflicting with higher-level assistant language behavior. While not a direct code-execution issue, this is a policy and UX control problem because the skill can force an unexpected language switch and reduce the user's ability to understand or verify safety-critical compliance advice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

All user-facing instructions, trigger phrases, and outputs are presented only in Chinese, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy issue unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.