While traveling, try recreating iconic scenes from classic movies in your photos!

• Outcome: Review
• Latest audit: Sep 16, 2026 · 4:41 AM UTC
• Version: 1.0.0

Overview

The skill does what it advertises, but it automatically uses and exposes precise location details in ways users should review before installing.

Review this skill before installing if you are uncomfortable with automatic IP-based location lookup or having precise coordinates/address-like details echoed in the chat log. Prefer giving a coarse city manually, avoid sharing a home/work address, and use the installer only for the platform you intend to update.

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
• Rogue Agent: Self-Modification, Session Persistence
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (9)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence

Finding

The declared purpose describes an end-user content skill focused on finding nearby filming locations and generating structured cinematic photography outputs. The supplied code does none of that. It is purely an installation utility: it detects supported assistant environments, computes install paths, creates directories, deletes any existing installation, and copies files into place. Those filesystem and platform-detection behaviors are undeclared and materially different from the described primary purpose. While an installer can be a supporting artifact for a skill package, this code chunk itself does not implement the advertised functionality at all, so the description does not accurately represent what the supplied code actually does.

Content

No source excerpt is available for this finding.

Missing User Warnings

High

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The skill instructs the agent to auto-detect the user's location via IP and collect precise coordinates to 6 decimal places, which can identify a very specific place. It does this without an upfront privacy notice, data-minimization rationale, or explicit opt-in before collection, creating a meaningful privacy and safety risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

High

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

The logging section directs the system to record and display exact coordinates and user-confirmed place information in visible output. Exposing sensitive location data in logs increases the risk of inadvertent disclosure, retention, or secondary use beyond the user's expectation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

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

Finding

The README states that the skill auto-detects the user's city via IP geolocation and relies on external services, but it does not clearly warn that the user's IP-derived location data may be transmitted to third parties. In a location-centric skill, this omission matters because users may unknowingly expose approximate location and related metadata to external providers, creating privacy and consent risks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The trigger conditions are broad enough that the skill could activate on casual travel, photography, or movie-related requests without clear user intent to share location or receive geolocation-based processing. That raises consent and privacy risks because subsequent steps immediately move toward IP-based location detection and precise nearby recommendations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 84% confidence

Finding

The instructions require storing the city name in 'Chinese + English' and mandate Chinese search queries alongside English ones. This imposes specific language behavior without offering the user a choice or explaining why those languages are required.

Content

No source excerpt is available for this finding.

Ssd 3

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill explicitly requires presenting precise user location details in the model's output logs, making sensitive data part of the response surface. Even if intended for transparency, surfacing exact coordinates and confirmed locations can expose the user's whereabouts to anyone viewing or storing the conversation.

Content

No source excerpt is available for this finding.

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 60% confidence

Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · install.sh (reported line 146)May include surrounding context.

sh

return 0
    fi

    # Create parent directory if needed
    mkdir -p "$(dirname "$install_path")"

    # Remove existing installation

Natural-Language Policy Violations

Low

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

Finding

The README's 'Or naturally' section provides trigger phrases in Chinese and English only, which may imply a language constraint without clarifying whether other languages are supported. Because no user language-choice or explicit limitation is documented, this can create an avoidable locale-policy ambiguity in the natural-language interface.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.