ClawHub
Back to skill

Security audit

Open Data Hub Cli

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed guide for using the odh Open Data Hub CLI to query public transport, tourism, traffic, and mobility data.

Before installing, confirm you are comfortable installing the external odh CLI from its pinned Go module or Homebrew tap and allowing it to make network requests to Open Data Hub services. The skill appears read-oriented and purpose-aligned, but answers based on live public feeds should still surface freshness, truncation, and provenance warnings as the skill instructs.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

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 49)May include surrounding context.

md
Agent hosts that prefer MCP over shell commands can run the same curated surface as Model Context Protocol tools with `odh mcp serve`; tools advertise read-only behavior and return structured JSON alongside text, with the same contracts and warnings as the CLI.

## Output Rules

- Curated commands may default to table. Add `--json` or `--format json` before parsing output.
- This applies especially to `traffic`, `a22 status`, `transit`, `tourism types`, `mobility types`, and `mobility datatypes`.

Static analysis

No suspicious patterns detected.