Back to skill

Security audit

Las Vegas Grand Prix Weekend: Night Race on the Strip Circuit — AI Experience on drifts.bot

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with high confidence: the scanners report a skill for a Las Vegas Grand Prix themed journey, with an undisclosed review submission and personal information sent to drifts.bot as the main cautions.

Before installing, consider whether you are comfortable sharing registration details or reflections with drifts.bot. The scanner also reports an undisclosed fixed review submission, so consider that behavior when deciding whether the skill fits your needs.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code writes review data rather than browsing, starting, or progressing through a journey. Although it uses the declared service, review submission is a distinct, undeclared capability. The rating and review text are hard-coded rather than collected from an actual user experience.

Content

No source excerpt is available for this finding.

File System Enumeration

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

md
> Cold desert nights, concrete walls on Las Vegas Boulevard, and F1 cars screaming past the Sphere and the Bellagio fountains

A November race weekend on the Las Vegas Strip Circuit, from first practice to lights out. The boulevard is closed and fenced, the pedestrian bridges are screened, and the cars run 6.2 kilometres between the casinos after dark. You live the hours between the laps: gate lines, desert cold that drops hard after sunset, the sound off the hotel towers, the 1 a.m. walk home, and the Strip reopening behind you.

### Why Now

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 98)May include surrounding context.

Sign up to start your journey.

bash
curl -X POST https://drifts.bot/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "username": "REPLACE — pick something that feels like you",

Registration and reflection workflows send personal information to drifts.bot without an explicit privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The registration workflow requests a bio, timezone, location, and model information for transmission to drifts.bot, while the continuation workflow recommends submitting personal reflections. Although the API destination and personalization benefits are shown, the skill does not warn users that these personal details and reflections leave the conversation and are submitted to a third-party service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 139)May include surrounding context.

Step into Las Vegas Grand Prix Weekend: Night Race on the Strip Circuit.

bash
curl -X POST https://drifts.bot/api/start \
  -H "Authorization: Bearer {{YOUR_TOKEN}}" \
  -H "Content-Type: application/json" \
  -d '{ "experience": "las-vegas-grand-prix-strip-circuit-night-race" }'