Back to skill

Security audit

tper-hellobus

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped transit helper that queries TPER's public Hellobus endpoint for Bologna and Ferrara bus arrivals.

Before installing, be aware that the skill sends stop code, line number, and optional time from your transit query to TPER's Hellobus service. It is best used when the request clearly involves TPER buses in Bologna or Ferrara; ambiguous bus questions may need confirmation.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger text is broad enough to match generic bus-arrival queries based on stop codes, line numbers, or mentions of Bologna/Ferrara, which can cause the skill to activate when the user did not specifically intend to use TPER. This is not a code-execution issue, but it can misroute requests, produce incorrect transit answers, and cause unnecessary external API calls.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The usage guidance repeats ambiguous conditions such as asking about bus arrivals, line numbers, or real-time tracking without sufficiently constraining geography or operator identity. In an agent-routing context, this can lead to over-selection of the skill, reducing reliability and potentially sending user-derived data to the wrong third-party service.

Static analysis

No suspicious patterns detected.