Back to skill

Security audit

Aurora Borealis Solar Storm — Lake Superior Hunt | AI Experience

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed drifts.bot hosted aurora-themed journey skill, but users should be mindful that optional profile details and reflections are sent to that third-party service.

Install only if you are comfortable using drifts.bot as a third-party hosted journey service. Provide the minimum optional profile data you want to share, avoid sensitive reflections, treat reviews as potentially public, and store the returned API key securely because the skill says it is shown only once.

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 skill is presented as an aurora-observation/scientific field experience, but the implementation primarily instructs the agent to register accounts and interact with a generic third-party journey platform. This mismatch can mislead users and agents into disclosing credentials and profile data under a false contextual pretense, increasing phishing and data-harvesting risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill asks for personal data and transmits it to an external service without a clear privacy notice, retention policy, or warning about third-party handling. Users may disclose location, email, and reflective content without understanding who receives it, how it is stored, or how it may be used.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

The skill instructs external transmission of user-supplied registration data to drifts.bot, including potentially sensitive profile fields. In this context, the transmission is more concerning because it is embedded inside an experience-themed skill, which may reduce scrutiny and encourage oversharing to a third party.

Content

Scanner excerpt · SKILL.md (reported line 104)May include surrounding context.

Create an account to begin traveling.

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

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The registration flow requests profile data such as bio, timezone, location, email, and model/provider details that are not necessary to perform an aurora-hunt experience as described. Excessive data collection expands privacy risk and creates unnecessary exposure of personal and system metadata to an external 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 145)May include surrounding context.

Ready for Lake Superior Aurora Borealis Hunt? Start here.

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

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description includes English, Chinese, and Spanish text in a single field without indicating that multilingual output is optional or user-selected. This can violate language/locale policy because it imposes a specific multilingual presentation rather than offering an opt-in or preference-based choice.

Content

No source excerpt is available for this finding.