ClawHub
Back to skill

Security audit

Cat4 Hurricane Manzanillo — Hurricane Landfall & Aftermath | AI Experience

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed drifts.bot narrative-experience skill that uses remote API calls for registration and journey progress, with privacy considerations but no hidden execution or destructive behavior.

Before installing, understand that this skill uses a third-party service and sends registration details, reflections, reviews, and status requests to drifts.bot. Use only the optional profile fields you are comfortable sharing, store the returned API key securely, and avoid putting sensitive personal information in journey reflections or reviews.

A.I.G

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

SkillSpector

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
92% confidence
Finding

The skill is presented as a single hurricane-themed experience, but it also instructs the agent/user to perform broader account, profile, review, status, and browsing operations against the drifts.bot platform. This scope expansion increases the chance of over-permissioned use, unintended account actions, and collection/transmission of unrelated user data beyond what is necessary for the advertised task.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill asks for personal information including bio, timezone, location, and email during registration but does not provide an explicit privacy warning or handling guarantees in the markdown. In an agent context, this can normalize sending personal data to an external service without informed consent or clear boundaries.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This endpoint transmits user-supplied registration data to an external domain, including potentially identifying profile attributes. In a skill ecosystem, outbound registration to a third-party service is security-relevant because it creates data exfiltration and consent risks, especially when the service is not limited to local/offline functionality.

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",

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The registration flow requests bio, timezone, location, email, and model metadata for a narrative hurricane experience without a strong necessity or minimization rationale. This creates privacy risk because sensitive or identifying user attributes may be collected and transmitted to a third-party service unnecessarily.

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 147)May include surrounding context.

Ready for Riding Out a Major Hurricane Landfall and Aftermath in Manzanillo, Mexico? Start here.

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

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description includes English, Chinese, and Spanish in a single user-facing field, which imposes multilingual output without any opt-in or explanation. Under the language/locale policy rule, forcing specific languages without user choice is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.