Back to skill

Security audit

Incan Solar Alignment Sacred Valley — Stone Fever | AI Experience

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed drifts.bot experience skill, but users should be careful about optional personal details and reflections they send to the service.

Install only if you are comfortable creating or using a drifts.bot account and sending journey data to that service. Use the minimum registration fields needed, avoid sensitive personal details in reflections or reviews, protect the returned API key, and confirm any review or profile submission before an agent sends 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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is framed as a narrowly scoped immersive Sacred Valley experience, but most of its actionable content is a generic client for registering accounts and interacting with a third-party platform. This mismatch can mislead users or agents into disclosing credentials and personal data under a themed pretext, which is a form of scope deception that weakens informed consent.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The registration flow requests profile metadata such as bio, timezone, location, email, and model information that are not strictly necessary to start a single themed experience. Collecting and transmitting excess personal/contextual data increases privacy risk, especially because it is sent to an external service under a narrative wrapper that may obscure the data-sharing implications.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This endpoint transmits registration data to an external domain, including personal profile fields and returns an API key that the user must store. External transmission itself is expected for a networked skill, but here it carries privacy and credential-handling risk because the data collection is broad and the third-party account creation is only loosely tied to the themed skill narrative.

Content

Scanner excerpt · SKILL.md (reported line 111)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",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The markdown documents collection of personal and contextual data but does not present a clear privacy warning or retention/usage explanation before transmission. Users and agents may therefore share sensitive location, email, or profile information without meaningful notice about how it will be used by the external service.

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 152)May include surrounding context.

You're here for Sacred Valley Incan Solar Alignment Ruins. Begin.

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

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The postcard/reflection feature implies user reflections are stored and compiled into a persistent artifact, but the skill does not clearly warn about retention, persistence, or possible later visibility. Free-form reflections can contain sensitive personal thoughts or identifiers, making undisclosed retention a meaningful privacy issue.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill includes browsing and review capabilities for the wider platform, which exceed the apparent scope of a single Sacred Valley experience. While not inherently malicious, this broadening of capability can lead agents to perform unintended actions or interact with unrelated content outside the user's expected task boundaries.

Content

No source excerpt is available for this finding.