Back to skill

Security audit

地产项目品牌故事线策略

Security checks for vulnerabilities and agentic risk

Overview

This is a real-estate marketing writing skill with disclosed file-reading and search steps, and I found no hidden execution, persistence, credential handling, or destructive behavior.

Before installing, be aware that the skill may read uploaded real-estate project files and automatically use web or image search to enrich marketing outputs. Avoid uploading confidential planning, pricing, or client materials unless you are comfortable with those materials being processed for this purpose.

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 (7)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill manifest defines very broad trigger phrases and explicitly requires invocation for nearly any real-estate-related writing request or uploaded project material. This can cause the skill to preempt more appropriate tools or user-directed workflows, creating prompt-routing hijack risk and reducing user agency over how their data and requests are handled.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill assigns output language by geography when the user has not explicitly chosen a language. This overrides user preference with an inferred attribute, which can produce unintended disclosures, incorrect language handling, or a degraded user experience in multilingual or cross-border contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The entire skill description is written only in Chinese and provides no indication that users may choose another language or locale. Under the policy rule for natural-language violations, this can be interpreted as imposing a language constraint without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The instruction '语言密度要高,每一句话都须承受得住细读' imposes a specific writing-style and language-density requirement as a default behavior. This is a natural-language policy concern because the file provides no user choice or opt-in regarding language or communication style.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file is entirely Chinese-language content and does not indicate that the skill is intentionally limited to Chinese-speaking users or a China-specific workflow. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Line L115 prescribes a locale/cultural-language preference based on project type: Chinese traditional projects should prioritize Chinese classics, while international/modern projects should prioritize Western writers or philosophers. This is a natural-language policy issue because it steers language/locale choice by default rather than offering the user an explicit choice or opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file presents all guidance in Chinese and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-language audience. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.