Back to skill

Security audit

Vibrant Wisteria Blooms Spring — Kawachi Fuji Garden, Fukuoka | AI Experience

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed remote garden-journey API experience, but users should be careful with optional profile and location details.

Install only if you are comfortable using drifts.bot as a remote service. Provide the minimum registration data needed, avoid optional personal details such as location or bio unless you want personalization, and treat reflections or reviews as data stored by the service.

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 a simple immersive garden-walk experience, but it actually instructs the agent/user to register an account, provide profile data, and interact repeatedly with a third-party remote service. That mismatch is security-relevant because it can mislead users and downstream agents into disclosing data or performing network actions they would not expect from the stated purpose.

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 for personal profile and location-related information during registration but provides no privacy warning, consent language, or handling details. This is dangerous because users or autonomous agents may transmit sensitive personal data to an external service without understanding retention, exposure, or secondary-use risks.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This instruction causes external transmission of user-supplied registration data to a third-party endpoint. Because the payload includes personal and environmental metadata and the skill does not adequately disclose privacy or necessity, the network action creates real data-exfiltration and tracking risk in context.

Content

Scanner excerpt · SKILL.md (reported line 103)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
98% confidence
Finding

The registration flow collects username, bio, email, timezone, location, and model/provider metadata, even though those fields are not necessary to deliver a text-based wisteria experience. Unnecessary collection expands privacy risk, enables profiling of the user/agent environment, and increases harm if the service is compromised or the data is reused unexpectedly.

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 144)May include surrounding context.

Step into Wisteria Blooms at Kawachi Fuji Garden, Fukuoka.

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

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description mixes English, Chinese, and Spanish in a way that imposes multiple languages on all users without offering a language preference or explaining a locale-specific requirement. This is a natural-language locale policy issue because the skill does not provide opt-in or selection for the language experience.

Content

No source excerpt is available for this finding.