Budapest

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 10:20 PM UTC
• Version: 1.0.0

Overview

This is a disclosed Budapest information guide with no executable code, hidden behavior, credential use, persistence, or privileged actions.

Installers should treat this as practical city guidance, not authoritative legal, medical, tax, immigration, or safety advice. Verify time-sensitive details with official Hungarian sources and apply judgment to subjective neighborhood or cultural descriptions.

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

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• YARA Signatures: Malware Match, Webshell Match, Cryptominer Match
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (17)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The invocation guidance says the skill should be used when a user asks about Budapest "for any purpose," which is a very broad condition without clear boundaries or exclusion cases. This can cause unintended activation on casual mentions of Budapest rather than explicit requests for city guidance.

Natural-Language Policy Violations

Medium

• Confidence: 93% confidence
• Finding: This section makes broad, categorical claims about Hungarians' personality traits at a national level. In a culture skill, such stereotyping can mislead users, reinforce bias, and produce discriminatory or culturally insensitive guidance even without malicious intent.

Natural-Language Policy Violations

Medium

• Confidence: 91% confidence
• Finding: The 'Hungarian Paradox' section presents behavioral stereotypes as if they broadly characterize an entire nationality. This is risky because it can normalize prejudicial assumptions and reduce the reliability of the skill's cultural guidance.

YARA rule 'network_reconnaissance': Network reconnaissance and scanning patterns [hacktools]

Medium

• Category: YARA Match

Content

g Hungarians

### National Character

Hungarians are often described as:
- **Proud**: Of history, language, culture
- **Pessimistic**: Famous for dark humor, melancholy
- **Intellectual**: Value education, chess, science
- **Hospitable**: Once you're in, you're in
- **Reserved initially**: Warm up over time

### The "Hungarian Paradox"

Hungarians can seem contradictory:
- Complain constantly but fiercely defend Hungary
- Pessimistic but achieved remarkable things
- Reserved but throw wild parties
- Traditional but embrace change

### Historical Context

Understanding helps:
- **1956 Revolution**: Deep national trauma
- **Communist era**: Still shapes older generation
- **Trianon (1920)**: Treaty that reduced Hungary's size — still sensitive
- **Habsburg history**: Complex relationship with Austria
- **Turkish occupation**: 150 years, left marks

## Language

### Why It Matters

Hungarian (Magyar) is:
- Not related to surrounding languages
- Finno-Ugric family (distant relatives: Fin

• Confidence: 65% confidence
• Finding: YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Natural-Language Policy Violations

Medium

• Confidence: 91% confidence
• Finding: The overview uses broad, unsupported negative generalizations such as 'less character' and frames whole districts as culturally inferior or impractical. In a city-guidance skill, this can mislead users, reinforce stigma toward neighborhoods and residents, and reduce trust in the skill's recommendations.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The district summaries include dismissive and class-coded labels like 'industrial,' 'working class,' and 'basic' without context, which stigmatize places rather than informing users objectively. Because the skill is meant to advise visitors and expats, these portrayals can unfairly bias housing and mobility decisions against certain communities.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The 'Generally Avoid' guidance gives categorical avoidance advice based on subjective safety perceptions, limited 'appeal for expats,' and claims like 'no real character.' In this context, that is harmful because users may treat the skill as authoritative and adopt discriminatory or inaccurate views about districts without evidence.

Natural-Language Policy Violations

Medium

• Confidence: 76% confidence
• Finding: The phrase "Few expat services" presents neighborhood suitability through an expat-centric lens, and the surrounding recommendations repeatedly target "people who know Budapest" or a particular outsider profile. This can function as an implicit locale/access preference in the skill content without offering alternative framing or user choice.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The guidance tells LGBTQ+ users to 'keep discrete' in public, which imposes a restrictive behavioral expectation on a protected group without sufficient context or user agency. Even if intended as safety advice, phrasing it this way can normalize unequal treatment, discourage authentic self-expression, and communicate that victims should self-limit rather than clearly explaining localized risk and allowing informed choice.

Autonomous Decision Making

Medium

• Category: Excessive Agency

Content

**Don't**:
- Jump/splash (not swimming pools)
- Be loud in thermal areas
- Take photos without consent
- Shave in pools (some do, don't be them)

### Health Considerations

• Confidence: 75% confidence
• Finding: Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: This file gives detailed immigration and visa guidance, timelines, eligibility rules, costs, and procedural steps without a prominent warning that these rules frequently change and must be verified with official Hungarian government sources before action. Users may rely on outdated or oversimplified legal information and make travel, work, or residency decisions that lead to denied applications, overstays, unlawful work, or other immigration consequences.

Natural-Language Policy Violations

Low

• Confidence: 79% confidence
• Finding: Under the language section, the text states 'Hungarian for local business' and 'English widely used in international' without explicitly framing this as optional or situational. Because SQP-3 covers language or locale policy violations, this can be flagged as a mild policy concern where a specific language is presented as expected without user opt-in.

Natural-Language Policy Violations

Low

• Confidence: 78% confidence
• Finding: SQP-3 applies to all file types and covers language or locale policy violations. This line presents Hungarian-language schooling as the default public-school option without any note about alternatives, user choice, or that this is a region-specific factual limitation, which can be read as enforcing a language constraint.

Missing User Warnings

Low

• Confidence: 89% confidence
• Finding: This markdown file extensively recommends bars, clubs, wine, beer, cocktails, and strong spirits, but provides only minimal cautionary language. While L198 says to take pálinka seriously and L329-L334 include general nightlife safety tips, the skill does not clearly warn users about responsible alcohol consumption, intoxication risks, or legal/health considerations despite centering on alcohol use.

Natural-Language Policy Violations

Low

• Confidence: 77% confidence
• Finding: The line states "Sunday: CLOSED (law)" as a blanket rule, which is a natural-language policy claim affecting user behavior and locale expectations. Because the file does not qualify or offer context, it presents a rigid locale-specific constraint that may mislead users rather than documenting a justified, scoped policy.

Natural-Language Policy Violations

Low

• Confidence: 78% confidence
• Finding: This markdown content includes Hungarian locale terms such as "Belváros-Lipótváros" and continues throughout with localized place names and street references. Under the natural-language policy check, forcing a specific language or locale without user opt-in can be a policy concern when no alternative or explanation is provided.

Natural-Language Policy Violations

Low

• Confidence: 79% confidence
• Finding: This markdown file contains a natural-language statement that normalizes a specific language expectation: 'English as working language (most tech)'. Under the policy rule for language or locale violations, statements that impose or assume a language without offering choice or explaining a region-specific necessity can be flagged.

Static analysis

No suspicious patterns detected.