ClawHub

HiFleet Claw

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed HiFleet vessel-position lookup skill, but users should treat the HiFleet token carefully.

Install only if you intend to query HiFleet vessel positions. Configure the HiFleet token as a secret, avoid logging full request URLs, and consider narrowing broad trigger terms if this runs in an assistant with many unrelated skills.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (11)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The Ship Position skill includes trigger terms such as “位置 / location” and “在哪 / where is,” which are common in ordinary conversation and can cause unintended activation. In an agent setting, overly broad activation can route unrelated user prompts into a skill that may access vessel-tracking data or invoke authenticated APIs, increasing the chance of privacy leakage or unintended external calls.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The Archive skill uses generic terms like “archive,” “ship info,” “owner,” and “manager,” which are not specific enough to reliably distinguish vessel-profile requests from normal discussion. This can lead to accidental skill invocation and exposure of company or vessel profile data when the user did not intend to access this function.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The Port skill trigger set includes broad phrases like “port,” “arrival,” and “departure,” which are common across logistics and everyday travel contexts. Without scope constraints, the agent may incorrectly activate the maritime port skill and fetch or display port-operation data for unrelated conversations.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The Performance skill includes generic terms such as “performance,” “speed,” and “efficiency,” which are highly ambiguous outside the shipping domain. This makes unintended invocation plausible and could result in disclosure of operational metrics or unnecessary calls to performance-analysis backends.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The Route skill uses generic terms such as “route,” “distance,” and “waypoint,” which also apply to common mapping and navigation requests unrelated to maritime operations. In an agent environment, this can misroute user intent and trigger unnecessary access to route-planning functions or associated data sources.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The Shipping skill contains especially broad terms like “market” and “news,” which can match many unrelated conversations. Because this skill appears to aggregate commercial and industry information, accidental activation could expose business-sensitive data or cause unneeded retrieval from external data services.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The Weather & Sea Conditions skill relies on words like “weather,” “wind,” and “visibility,” which are extremely common in general conversation. This is risky because unrelated weather questions may incorrectly trigger a maritime advisory skill, potentially causing confusion, unnecessary external requests, or inappropriate voyage-related advice.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The document states that the implemented Ship Position skill requires a `usertoken`, but provides no guidance on secure credential storage, transmission, redaction, or scope. In agent ecosystems, undocumented token handling is dangerous because users or integrators may pass secrets insecurely in prompts, logs, or client-side configuration, leading to credential leakage and unauthorized API access.

External Transmission

Medium
Category
Data Exfiltration
Content
| 项目 | 值 |
|------|-----|
| **简要描述** | 获取（岸基+卫星+移动）船舶最新位置信息 |
| **请求 URL** | `https://api.hifleet.com/position/position/get/token` |
| **请求方式** | `GET` |

### 请求 Query 参数
Confidence
85% confidence
Finding
https://api.hifleet.com/

External Transmission

Medium
Category
Data Exfiltration
Content
1. **检查 token**：若未配置 `usertoken`，返回提示并终止。
2. **校验 MMSI**：请求必须包含有效 `mmsi`（9 位数字字符串）。
3. **发起请求**：`GET https://api.hifleet.com/position/position/get/token?mmsi={mmsi}&usertoken={usertoken}`
4. **解析结果**：根据 `result === "ok"` 与 `list` 解析位置与船舶信息；若 `result !== "ok"`，按错误处理并提示用户。

---
Confidence
92% confidence
Finding
https://api.hifleet.com/

External Transmission

Medium
Category
Data Exfiltration
Content
```text
# 获取 MMSI 413829443 的最新船位
GET https://api.hifleet.com/position/position/get/token?mmsi=413829443&usertoken=${HIFLEET_USER_TOKEN}
```

解析后向用户展示时，建议包含：船名、MMSI、最后更新时间、经纬度（度）、航速、航向、目的港、状态。
Confidence
94% confidence
Finding
https://api.hifleet.com/

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal