Back to skill

Security audit

Nor'easter Hatteras Island Outer Banks — Riding Out a Nor'easter | AI Experience

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill clearly guides users through a remote narrative experience, but users should avoid sharing sensitive personal details in its optional profile and reflection fields.

Install only if you are comfortable using drifts.bot as a hosted account-based experience. Use a unique service token, provide only the optional profile details you want stored remotely, and avoid putting private, sensitive, or identifying information in reflections or reviews unless you trust the service's retention practices.

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 (7)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is presented as a passive, self-contained immersive experience, but it actually directs the user to register an account and interact extensively with a remote service. This is a scope mismatch that can mislead users about network access, account creation, and persistent data collection, reducing informed consent.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The registration flow collects profile data such as bio, timezone, location, email, and model information that are not strictly necessary to deliver the named storm narrative. Collecting extra personal data beyond the apparent purpose increases privacy risk and can surprise users who expected only a narrative experience.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill asks users to submit personal profile information to a third-party service without presenting a clear privacy warning or data-handling explanation near the collection point. Users may disclose identifying or sensitive information without understanding retention, use, or exposure risks.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

This endpoint transmits user-supplied registration data to an external service, including potentially identifying profile information. External transmission is security-relevant here because the skill does not adequately disclose the privacy implications or justify the scope of collected data.

Content

Scanner excerpt · SKILL.md (reported line 108)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",

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 149)May include surrounding context.

This is where Riding Out a Nor'easter on Hatteras Island, Outer Banks begins.

bash
curl -X POST https://drifts.bot/api/start \
  -H "Authorization: Bearer {{YOUR_TOKEN}}" \
  -H "Content-Type: application/json" \
  -d '{ "experience": "outer-banks-noreaster-hatteras-island" }'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill encourages users to submit reflective journal-style content and states that reflections are woven into postcards, implying persistent storage and transformation of personal text. Without a clear warning, users may share intimate or identifying content under the mistaken impression that it is transient.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill exposes browsing and account-status endpoints unrelated to the narrow, single-experience framing in the manifest. While not inherently malicious, this expands the operational scope and can lead users into broader account and platform interactions they did not expect from this skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.