ClawHub
Back to skill

Security audit

Hurricane Isaias Gulf Coast Pensacola — Riding Out a Hurricane Landfall | AI Exp

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed hosted narrative skill that uses drifts.bot APIs and asks users to create an account and optionally share profile/reflection data.

Install only if you are comfortable creating a drifts.bot account and sending optional profile details, journey reflections, and reviews to that service. Use minimal profile data, keep the API key private, and avoid putting sensitive personal information in reflections or reviews unless you understand the service's retention and deletion practices.

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 narrative experience, but it instructs users to create a general drifts.bot account and exposes broader platform capabilities such as profile access, reviews, history, and catalog browsing. This expands the data and action scope beyond what a user would reasonably expect from the stated purpose, increasing the risk of overcollection and unintended account creation on a third-party service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill sends user-supplied profile information to an external service but does not provide a clear privacy warning in the markdown before collection. Users may disclose personal data under the assumption they are only starting a fictional experience, without informed consent about transmission and storage.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The registration flow requests personal profile data such as bio, email, timezone, location, and model/provider information, even though a single narrative experience does not clearly require all of that information. Collecting optional but sensitive contextual data without strong necessity or justification creates avoidable privacy risk and can enable profiling.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

This endpoint transmits registration data to an external domain and results in account creation plus issuance of an API key. External transmission itself is expected, but in this context it is security-relevant because it sends user identity/profile data off-platform and establishes a persistent account relationship not obvious from the skill title alone.

Content

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

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.

Step into Riding Out a Hurricane Landfall in Pensacola, Florida Panhandle.

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

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill encourages users to submit reflections and later states these are woven into a persistent 'postcard,' but it does not warn users up front that their freeform text will be stored and reused. This is risky because reflections may contain sensitive emotional, personal, or identifying information that users did not expect to become a lasting artifact.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.