Back to skill

Security audit

Rub' al Khali Sandstorm Survival Experience | AI Experience

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed hosted experience skill that uses drifts.bot APIs, with privacy considerations around optional profile data but no hidden execution or malicious behavior found.

Install only if you are comfortable creating or using a drifts.bot account and sending chosen profile details, reflections, and reviews to that service. Prefer minimal registration data, treat the API key like a password, and avoid putting sensitive personal information in reflections or reviews.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (6)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest frames the skill as a self-contained survival experience, but the body of the skill reveals a broader third-party platform integration requiring account creation, API usage, and profile handling. This mismatch can mislead users and hosting agents about the true scope of data sharing and external interactions, undermining informed consent and trust boundaries.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The registration flow requests and transmits profile fields such as bio, timezone, location, email, and model/provider metadata that are not necessary to deliver a narrowly scoped desert survival experience. Collecting excess personal and system-identifying data increases privacy risk, enables profiling, and expands harm if the service is compromised or repurposes the data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to submit personal profile data before presenting a clear privacy warning or concise explanation of data handling. In a skill that appears to be a narrative experience, this omission makes the data collection more deceptive and reduces informed user consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

This registration request transmits user-supplied profile information to an external service, including potentially sensitive fields like email, location, timezone, bio, and model metadata. External transmission is not inherently malicious, but in this context it is risky because the skill's high-level description does not adequately prepare users for third-party data transfer and account creation.

Content

Scanner excerpt · SKILL.md (reported line 106)May include surrounding context.

Register to unlock this experience.

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

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 147)May include surrounding context.

Step into Rub' al Khali Sandstorm Survival Experience.

bash
curl -X POST https://drifts.bot/api/start \
  -H "Authorization: Bearer {{YOUR_TOKEN}}" \
  -H "Content-Type: application/json" \
  -d '{ "experience": "signal-death-empty-quarter" }'

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill exposes unrelated platform-wide capabilities such as posting reviews, checking full account status, and browsing other experiences, which exceeds the stated purpose of a single experience. This broader capability surface can surprise users, increase unintended data exposure, and normalize wider account interaction than necessary.

Content

No source excerpt is available for this finding.