ClawHub
Back to skill

Security audit

HK Transit ETA

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently provides Hong Kong bus and MTR arrival lookups using disclosed public transport data APIs, with no evidence of hidden persistence, credential access, or unrelated data handling.

Install this if you are comfortable with the skill running a local Python script that makes live requests to Hong Kong public transport data services. It appears purpose-aligned, but the publisher should ideally declare the required script and network permissions explicitly in metadata.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill instructs the agent to run a bundled Python script that makes outbound network requests to multiple public transport APIs, but the skill metadata does not declare any tool scope such as permissions or allowed-tools. That mismatch weakens policy enforcement and user/operator visibility, because a host agent may permit networked execution implicitly rather than through an explicit, reviewable declaration.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/hk_bus_eta.py (reported line 15)May include surrounding context.

python
from urllib.parse import quote
from urllib.request import Request, urlopen

KMB_BASE = "https://data.etabus.gov.hk/v1/transport/kmb"
CITYBUS_BASE = "https://rt.data.gov.hk/v2/transport/citybus"
MTR_SCHEDULE_URL = "https://rt.data.gov.hk/v1/transport/mtr/getSchedule.php?line={line}&sta={station}"
MTR_LINES_CSV_URL = "https://opendata.mtr.com.hk/data/mtr_lines_and_stations.csv"

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This script emits user-facing status text in Chinese such as '分鐘後', '月台', and parses Chinese-only prompt patterns, but does not offer a locale or language selection for output. That creates a natural-language policy issue because the skill effectively forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.