Security audit

城市更新改造现场分析

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow urban-renewal photo analysis skill with no executable code, persistence, or hidden data access.

Install this if you want Chinese-language urban-renewal photo analysis and renovation prompt drafting. Review the broad trigger phrases if you run many skills, because generic prompt-generation requests could activate this skill unintentionally.

A.I.G

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

SkillSpector

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 (5)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger phrases are broad enough to match ordinary requests about analyzing a site or generating prompts, without tightly constraining that the request must involve urban-renewal photo analysis. In a multi-skill agent, this can cause unintended activation and prompt hijacking of unrelated conversations, leading the assistant to apply the wrong workflow or expose capabilities outside the intended scope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The file is written as a Chinese-only skill and presents all headings, workflow, triggers, and interaction norms in Chinese, with no indication that users may choose another language. This creates a locale/language constraint that is not documented as optional or justified as region-specific compliance behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill declares that any listed expression can trigger it but does not define clear boundaries, prerequisites, or disambiguation rules. That increases the chance of accidental invocation on adjacent requests, which is dangerous because the skill then forces a rigid workflow and immediate analysis behavior that may override more appropriate handling.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This markdown file presents all instructions and scoring criteria only in Chinese, and it 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, forcing a specific language without user opt-in is a natural-language locale violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This markdown file contains user-facing instructional content exclusively in Chinese, while the policy requires flagging language or locale constraints that are imposed without user opt-in. There is no indication that the skill is region-specific or that users may choose another language.
Content: No source excerpt is available for this finding.