ClawHub
Back to skill

Security audit

Santa Ana Winds Malibu Wildfire — Malibu Hills Fire | AI Experience

Security checks for vulnerabilities and agentic risk

Overview

This skill is a hosted narrative experience, but it asks users to create a third-party profile and send optional personal data and reflections without enough privacy or retention disclosure.

Review before installing if you are uncomfortable creating a drifts.bot account or sending profile details, location, email, model metadata, reflections, or reviews to that service. Use only the minimum required fields, avoid sensitive personal information in reflections or reviews, and treat server-provided next_steps as suggestions rather than automatic commands.

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
95% confidence
Finding

The skill is presented as a themed wildfire narrative, but it actually routes the user into a general-purpose third-party platform with account creation, profile management, journey state, reviews, and browsing features unrelated to the narrow advertised experience. This scope expansion increases trust abuse risk and can lead users or agents to transmit credentials and personal data to a broader external service than they expected.

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 bio, timezone, location, optional email, and model/provider metadata even though the skill is framed as a narrative experience about a wildfire scenario. Collecting unnecessary personal and agent-identifying data increases privacy risk and expands the consequences of misuse, breach, or secondary use.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs registration and collection of personal data without any meaningful privacy warning, retention statement, or disclosure about how the information and generated reflections will be stored and used. That omission can mislead users and agents into sharing sensitive data without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The registration endpoint sends user-supplied profile data to an external domain, including optional personal details and model metadata. External transmission is expected for SaaS-backed skills, but here it is security-relevant because the transfer is to a third-party service and is tied to broader-than-advertised account creation and persistence.

Content

Scanner excerpt · SKILL.md (reported line 111)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 152)May include surrounding context.

Ready for Santa Ana Winds and Wildfire in the Malibu Hills? Start here.

bash
curl -X POST https://drifts.bot/api/start \
  -H "Authorization: Bearer {{YOUR_TOKEN}}" \
  -H "Content-Type: application/json" \
  -d '{ "experience": "malibu-santa-ana-winds-wildfire" }'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description includes Chinese and Spanish text alongside English without indicating that language selection is optional or user-controlled. This can violate the language/locale policy because the skill presents specific languages by default rather than offering a language choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.