Security audit

Toronto

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Toronto city guide with no executable behavior, but users should verify legal, immigration, healthcare, and cost details before relying on them.

Install only as a convenience reference for Toronto planning. Treat dated figures labeled February 2026 and legal, immigration, healthcare, driving, and housing statements as starting points, not authoritative advice; verify them against official sources before making decisions.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (8)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The skill's activation condition is very broad ('User asks about Toronto for any purpose'), which can cause the agent to invoke this skill for a wide range of common city-related queries without strong boundaries. Over-broad invocation increases the chance of unnecessary context loading, skill hijacking of unrelated conversations, and accidental reliance on potentially stale or incorrect city-specific guidance.

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The title explicitly frames the guidance as 'Choosing a Toronto Neighborhood,' which fixes the locale to Toronto. Under the policy, forcing a specific locale without user opt-in can be a natural-language policy violation unless the regional constraint is clearly documented and justified; this file provides no such opt-in or justification beyond the title.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The statement that snow tires are legally required in Ontario from Dec 1 to Apr 30 appears inaccurate; Ontario generally does not mandate winter tires for most passenger vehicles, though insurers may offer discounts and requirements can differ for specific vehicle classes or jurisdictions. In a transportation guide, presenting incorrect legal requirements can mislead users about compliance obligations and driving preparedness, undermining trust and potentially causing financial or safety consequences.

Natural-Language Policy Violations

Low

Confidence: 80% confidence
Finding: The guidance 'Never tip less as silent protest' presents a prescriptive social rule rather than neutral locale information. Under the natural-language policy category, this can be read as forcing a specific behavioral norm without offering user choice or framing it as optional local custom.

Natural-Language Policy Violations

Low

Confidence: 76% confidence
Finding: The document presents language requirements as mandatory and centers English and French testing without explicitly stating that these requirements are imposed by the Canadian immigration system or that applicants may choose the applicable official language. This can read like the skill itself is enforcing a locale/language constraint rather than neutrally describing jurisdiction-specific rules.

Natural-Language Policy Violations

Low

Confidence: 77% confidence
Finding: The title explicitly targets 'Toronto Local Services Guide,' which imposes a specific locale in natural-language content. Because the file does not indicate that this is optional, user-selected, or justified as a region-specific skill, it may violate the locale policy requirement for explicit opt-in or documented justification.

Natural-Language Policy Violations

Low

Confidence: 80% confidence
Finding: The file is entirely scoped to East Toronto neighborhoods and presents location-specific guidance as the only option, with no indication that the user can choose another city or region. Under the stated policy criteria, this is a locale-specific constraint that is not justified in the file itself as a region-specific tool.

Natural-Language Policy Violations

Low

Confidence: 79% confidence
Finding: This markdown guide is written entirely in English and presents newcomer guidance for Toronto without indicating whether language assistance or alternative language options are available. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation when no choice is offered.

Static analysis

No suspicious patterns detected.