Back to skill

Security audit

Flash Flood Desert Survival — Oman Wadi Shab | AI Experience

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed hosted story-experience skill that uses drifts.bot account APIs, with optional profile data users should avoid providing unless comfortable.

Install only if you are comfortable using drifts.bot as a hosted account service. Use a non-sensitive username and provide optional fields like bio, location, timezone, email, and model details only if you want personalization and accept sharing them with that service. Keep the API key private.

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
96% confidence
Finding

The skill is presented as a single survival-themed narrative experience, but the implementation directs users into a broader account-based platform with registration, profile handling, reviews, and browsing of unrelated experiences. This mismatch undermines informed consent and can trick users into disclosing data or authorizing actions beyond what the skill description reasonably suggests.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The registration flow requests personal information, including email, timezone, location, bio, and model/provider details, without any visible privacy notice, retention statement, or explanation of sharing practices. In a skill context, this can cause users or agents to transmit identifying data without understanding how it will be used or stored.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

This endpoint transmits user-supplied registration data to an external domain, including optional personal profile information and potentially identifying metadata. External transmission is risky here because the skill does not provide sufficient privacy framing, and the user may not expect account creation with a third-party service from the themed description alone.

Content

Scanner excerpt · SKILL.md (reported line 106)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",

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The registration flow collects profile data such as bio, timezone, location, email, and model metadata that are not necessary to deliver the stated flash-flood narrative experience. Excessive collection increases privacy risk and expands the consequences of compromise, especially when users may believe they are only starting a self-contained themed experience.

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 Oman Wadi Flash Flood Survival? Start here.

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

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill exposes review posting and browsing across the wider experience catalog, which goes beyond the claimed single-experience purpose. While not inherently dangerous, this scope expansion can surprise users and broadens the attack surface and data-sharing footprint relative to the advertised functionality.

Content

No source excerpt is available for this finding.