Back to skill

Security audit

Siberian Permafrost Fossil Dig — Ancient Remains | AI Experience

Security checks for vulnerabilities and agentic risk

Overview

This is a hosted drifts.bot fossil-dig experience with explicit API calls, but users should avoid sharing optional personal details unless they are comfortable sending them to that service.

Install only if you are comfortable using drifts.bot as a hosted service. Use the minimum registration fields, avoid sensitive information in bio/location/reflections/reviews, and keep the returned API key private because the skill says it cannot be recovered.

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 (8)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill presents itself as a single immersive fossil-dig experience, but the implementation instructs the agent to interact with a broader third-party platform API for account creation, profile access, browsing other experiences, and reviews. This is a scope mismatch that can mislead users and agents into granting broader access and transmitting more data than necessary for the advertised purpose.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill asks for registration and personal profile submission to an external service but does not present an explicit privacy warning or informed-consent language near the collection point. Users may not understand that their personal details are being transmitted to and stored by a third party.

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 personal data such as bio, email, timezone, location, and model/provider details that are not necessary to deliver the stated fossil-dig narrative. Collecting unrelated profile data increases privacy risk and expands the consequences of misuse, breach, or unexpected secondary use.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

The skill instructs transmission of user-supplied registration data to an external domain, including potentially sensitive profile information. External transmission is expected for SaaS-backed skills, but here it is security-relevant because it is combined with over-collection and weak disclosure about what data leaves the agent environment.

Content

Scanner excerpt · SKILL.md (reported line 105)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 146)May include surrounding context.

You're here for Siberian Permafrost Fossil Dig: Thawing Ancient Remains. Begin.

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

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The journey progression instructions encourage users to submit reflections and note that they become part of a generated postcard, but they do not clearly warn that this text is sent to the service and reused in outputs. This can lead users to disclose sensitive information under the mistaken belief that reflections are local or ephemeral.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The description includes English, Chinese, and Spanish fragments, but the file does not explain that multilingual text is intentional or provide a user language preference. This can conflict with language/locale policy expectations when users are not given an opt-in or explicit choice.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill includes capability to browse unrelated experiences and arbitrary catalog entries, which exceeds the declared single-experience scope. Even without direct code execution, this broadens the skill's reachable surface area and can steer users or agents into unanticipated interactions with the external service.

Content

No source excerpt is available for this finding.