ClawHub
Back to skill

Security audit

HK Bus ETA

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Hong Kong transit ETA helper that runs a local Python script and queries disclosed public transit data endpoints.

Install only if you are comfortable with the skill sending transit lookup details such as route numbers and station codes to the documented public transport data services. Avoid sharing precise live-location coordinates unless needed for stop selection.

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
94% confidence
Finding

The skill instructs the agent to run a bundled Python script that queries multiple external transport APIs, but the manifest declares no explicit tool scope such as network permissions or allowed tools. That mismatch weakens security boundaries because an agent or reviewer cannot tell from the declaration that external network access is required, increasing the chance of overbroad execution or unsafe approval in environments that rely on manifest metadata for policy enforcement.

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
91% confidence
Finding

This script emits user-facing status and ETA text with hard-coded Chinese phrases such as '分鐘後' and '月台' in normal output mode. The file does not offer a language or locale selection, so it effectively forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.