Back to skill

Security audit

City of Toronto Open Data

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed City of Toronto open-data helper that queries the public CKAN API and keeps only a small local cache.

Installers should understand that the skill may be invoked for broad Toronto transit or housing questions, and it may create a temporary local cache while querying Toronto's public open-data API. It does not request credentials or modify user data.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases include broad topical terms like "toronto transit" and "toronto housing," which can cause the skill to activate for general user requests that are only loosely related to the City of Toronto open data portal. This can lead to unintended tool invocation and over-broad routing, especially because the skill has Bash permission and may be selected in contexts where a more specific skill or no tool use would be safer.

Static analysis

No suspicious patterns detected.