Back to skill

Security audit

徒步路线规划

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language hiking planner that uses a local template and asks users to verify safety-critical route information.

Install this if you want Chinese-language hiking plans based on a fixed local template. Before relying on an itinerary, verify current weather, closures, daylight, permits, transport schedules, and emergency options from official sources, especially for real-world group outings.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (4)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

md
- 若优先公共交通,优先选择起终点都靠近站点、返程班次稳定的路线;不要只为了景观牺牲返程确定性。
- 若精确里程、爬升或耗时无法核实,使用范围值,并写明估算依据,不要伪装成精确数据。

## Output Rules

- 默认用中文输出。
- 优先复用本地固化模板的章节名和字段名;仅在缺少徒步安全字段时补充必要栏目。

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The metadata presents the skill name, description, and default prompt exclusively in Chinese without evidence of user locale selection or consent. If surfaced to users who are not expecting Chinese, this can create misunderstanding of safety notes, transport details, timings, or risk warnings, which is more serious here because the skill produces real-world outdoor itineraries that may be followed operationally.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The default prompt activates the skill for broadly defined hiking-planning requests and only requires a minimal follow-up when key constraints are missing. That loose trigger can cause the skill to engage in situations where the user did not clearly request this specialized planner, increasing the chance of unintended routing, safety, or logistics advice being injected into a conversation. In a route-planning skill, mistaken activation matters because outputs may be treated as actionable real-world guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction "默认用中文输出" imposes a language preference in the skill's behavior without mentioning user opt-in or an option to choose another language. This matches the policy category for language or locale constraints that are not presented as optional.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.