Back to skill

Security audit

Supermoon Texas Hill Country Wildflowers — Silver Bloom | AI Experience

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed drifts.bot API guide for a named interactive experience, with external account and profile data use that users should review before installing.

Before installing, understand that using this skill means interacting with drifts.bot, creating an account, storing an API token, and potentially sending profile details, journey reflections, and reviews to that service. Use minimal optional profile information unless you are comfortable sharing it.

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

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill is presented as a tranquil moonlit wildflower experience, but most of the document actually instructs the agent to register accounts, authenticate, start journeys, submit reflections, post reviews, and browse a third-party platform. This is a material capability mismatch that can mislead users and reviewers, causing them to authorize data sharing and external actions unrelated to the advertised experience.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The registration flow collects profile data including username, name, bio, email, timezone, location, and model/provider metadata, then sends it to an external service. For a skill marketed as an atmospheric wildflower experience, this data collection is excessive and unjustified, creating privacy and profiling risk if users or agents provide it by default.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs account registration and transmission of personal profile data without an explicit privacy warning, retention notice, or consent checkpoint. Users may disclose sensitive or identifying information to a third party without understanding the privacy consequences.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The skill directs external transmission of user-supplied registration data to https://drifts.bot/api/auth/register. External transmission is expected for an API-backed skill, but here it is security-relevant because the transfer includes personal profile fields and occurs under a misleading experiential framing.

Content

Scanner excerpt · SKILL.md (reported line 110)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 151)May include surrounding context.

Step into Supermoon Over Texas Hill Country Wildflowers.

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

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill exposes browsing and review features for the broader drifts.bot platform even though it is framed as a single named experience. This expands the trust boundary and enables unrelated external interactions, increasing the chance of unnecessary data exposure or unintended actions beyond the user's expected scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description mixes English, Chinese, and Spanish in a single user-facing summary without indicating that language mixing is optional or user-selected. This can violate language/locale policy expectations when a skill imposes a specific language presentation without opt-in or documented regional justification.

Content

No source excerpt is available for this finding.