Madrid

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 8:44 PM UTC
• Version: 1.0.0

Overview

This is a Markdown-only Madrid guide with some dated or oversimplified practical advice, but no hidden code, persistence, credential handling, or destructive behavior.

Before installing, treat this as practical travel and relocation guidance, not authoritative legal, medical, immigration, housing, or financial advice. Verify visa rules, healthcare eligibility, rent limits, transport prices, and safety conditions with current official or trusted local sources, and be cautious when sharing identity or financial documents with landlords or agents.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (9)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The activation condition says the skill should be used when a user asks about Madrid "for any purpose," which is overly broad and can cause the agent to invoke this skill in situations where a narrower or more appropriate skill should handle the request. While this skill is informational rather than directly code-executing, overbroad routing can still degrade safety and reliability by overshadowing more specialized guidance or causing irrelevant instructions to be loaded.

Natural-Language Policy Violations

Low

• Confidence: 79% confidence
• Finding: This markdown file contains natural-language phrasing that presents one cuisine style as the authentic or real version, which can be interpreted as an unsupported normative policy or locale/culture preference. Because the guidance is framed categorically rather than as a user-selectable preference, it risks violating the requirement to avoid forced language/locale-style constraints without opt-in.

Natural-Language Policy Violations

Low

• Confidence: 77% confidence
• Finding: This guide contains substantial bilingual content such as 'Sanidad Pública', 'Ayuntamiento', 'Urgencias', and other Spanish-only labels embedded in an otherwise English document. Under the language/locale policy, forcing or assuming a specific locale without user opt-in can be a natural-language policy issue when no language preference is documented.

Natural-Language Policy Violations

Low

• Confidence: 76% confidence
• Finding: This markdown file is entirely written in English while describing neighborhoods in Madrid, but it does not indicate that the user opted into English or that the locale is intentionally fixed. Under the language/locale policy rule, forcing a specific language without user opt-in can be a natural-language policy concern.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: This section advises users to provide passports, NIEs, employment contracts, payslips, and bank statements to landlords during the rental process, but gives no warning about document minimization, redaction, or fraud risks. In a relocation guide, readers may be inexperienced and more likely to share full sensitive documents with unverified agents or listings, increasing exposure to identity theft or financial fraud.

Missing User Warnings

Low

• Confidence: 92% confidence
• Finding: The student visa section gives specific work-permission and application guidance as if it were stable, but immigration rules, permitted work hours, documentation, and deadlines can change. Users relying on outdated visa advice could violate immigration conditions, lose legal status, or make costly travel and enrollment decisions based on incorrect information.

Missing User Warnings

Low

• Confidence: 94% confidence
• Finding: The healthcare section labels access as 'Free!' and presents a simple path to coverage, which can mislead users into assuming universal eligibility regardless of residency, insurance, employment, or student status. On a safety-critical topic, overstating access may cause users to forgo required insurance, delay care, or face unexpected denial of service or medical costs.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: The nightlife section encourages late-night drinking, bar hopping, and clubbing until 6-7am without any safety framing, moderation advice, or transport/personal-security guidance. In a travel skill, users may rely on the itinerary as practical guidance, so omission of basic cautions can contribute to risky situations such as intoxication, theft, harassment, or being stranded late at night.

Natural-Language Policy Violations

Low

• Confidence: 87% confidence
• Finding: The 'Useful Phrases' section provides only Spanish phrases and presents them as the expected interaction mode for the visitor guidance. Under the policy, language constraints should not be forced without user opt-in or an explicit choice, and this file does not offer alternatives or note that the phrases are optional.