Mumbai

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 11:02 PM UTC
• Version: 1.0.0

Overview

This is a static Mumbai guide skill with practical travel, relocation, business, visa, food, transport, safety, and healthcare information, and I found no hidden execution, credential access, persistence, or exfiltration behavior.

Install only if you want a Mumbai reference guide. For healthcare, visa, tax, housing, school, business, or safety decisions, use it as a starting point and confirm details with official sources or qualified local professionals because prices, rules, and conditions can change.

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

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (13)

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The activation rule 'User asks about Mumbai for any purpose' is extremely broad and can cause the skill to trigger on many loosely related queries, increasing the chance of irrelevant guidance being injected into conversations. While not directly enabling code execution or data theft, overbroad invocation can degrade agent behavior, override more appropriate skills, and amplify any inaccuracies in the skill's content.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium

• Category: Excessive Agency
• 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.

Content

Scanner excerpt · business.md (reported line 221)May include surrounding context.

md

| Route | Meaning | Sectors |
|-------|---------|---------|
| Automatic | No approval needed | Most sectors |
| Approval | Government approval | Defense, media, etc. |

### Key Sectors (Automatic Route)

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

This section gives actionable emergency and health guidance but does not clearly state that the document is informational only and not a substitute for professional medical advice or urgent care. In a healthcare-oriented skill, users may rely on the guidance during acute situations, which could delay appropriate treatment or cause them to choose suboptimal care paths.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

Stating a fixed language priority ('Hindi and Marathi are primary. English widely spoken in business.') without user opt-in can bias the assistant toward assumptions about preferred language or communication style. In context this is not a severe security issue, but it can lead to inappropriate responses, reduced usability, or culturally insensitive behavior if the agent infers language preference instead of asking.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 81% confidence

Finding

Lines L034-L036 state that English works only in certain areas, that basic Hindi is very helpful elsewhere, and that Marathi is appreciated. In a policy context, this can be read as steering users toward specific languages without explicit opt-in or a clear statement that language use is optional based on user preference and context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 79% confidence

Finding

The phrase "Most common 'Indian food' for foreigners" introduces a user-group-specific framing that can reflect an unjustified locale/audience assumption in natural language guidance. This is not presented as an optional audience preference or a region-specific compliance constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 80% confidence

Finding

The document tells users to say "bas" and elsewhere provides fixed Hindi/Marathi ordering phrases, which imposes a specific language expectation in the guidance. Under the policy, locale or language constraints should be optional, justified, or presented with user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 82% confidence

Finding

The guide highlights 'English-speaking staff' as a characteristic of premium hospitals, which introduces a language preference into the skill content without offering users a language or locale choice. Under the policy, language-related assumptions should either be optional, user-selected, or clearly justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 79% confidence

Finding

This markdown file gives concrete housing cost, transit, and lifestyle guidance that users may rely on for relocation or budgeting decisions, but it does not include any disclaimer that prices, commute times, and local conditions can change. Under the markdown-file warning criterion, this is a mild omission because the content could affect user data or important personal decisions if treated as definitive.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 77% confidence

Finding

Line L117 introduces a locale/language expectation in natural language without clarifying that it is optional guidance or context-dependent. Under the policy rule, language-related constraints can be problematic when presented as a presumed requirement rather than a user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 78% confidence

Finding

The guide instructs users to complete FRRO registration at a specific government website but does not mention any language or locale considerations, effectively assuming the user can operate in the default language environment. Under the policy rule for natural-language violations, files should not force a language or locale without opt-in or justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

The guide recommends visiting Marine Drive at sunset or after dark because of the lights, but it does not include any basic personal-safety caveats such as staying in well-populated areas, avoiding isolated stretches, and using trusted transport late at night. In a travel guidance skill, omission of safety context can normalize risky behavior for unfamiliar visitors, especially solo travelers.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The itinerary recommends late-night bar hopping and visits to potentially sensitive or higher-risk areas without any safety context, such as situational awareness, transport precautions, or guidance on guided visits. In a travel skill, omission of basic safety warnings can increase the chance that users enter unfamiliar environments unprepared, especially solo travelers or first-time visitors.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.