Back to skill

Security audit

Hodge Conjecture Algebraic Geometry — Millennium: Hodge Conjecture | AI Experien

Security checks for vulnerabilities and agentic risk

Overview

This is a hosted math-experience skill that clearly uses drifts.bot accounts and API calls, with privacy considerations around optional profile data but no hidden local code or deceptive behavior found.

Install only if you are comfortable using drifts.bot as a hosted service. Use a unique username, omit optional profile fields unless you want personalization, protect the returned API key, and review any reflection or public review text before sending 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
96% confidence
Finding

The skill is presented as a math/educational exploration, but it instructs the agent to create persistent remote accounts and interact with a third-party service. That is a scope mismatch: users may invoke the skill expecting local educational guidance, while the skill actually causes account creation and ongoing external state changes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill directs collection of profile and contextual data during registration without any explicit privacy warning, consent language, or retention notice. In an agent setting, this is dangerous because users may not realize their personal data is being transmitted to a third-party service and stored persistently.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

The skill instructs the agent to transmit user-supplied registration data to an external domain, including profile attributes and potentially email and model metadata. External transmission is especially sensitive here because it is tied to account creation and persistent storage on a third-party service outside the user’s immediate expectation from an educational math skill.

Content

Scanner excerpt · SKILL.md (reported line 112)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",

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The registration flow collects optional personal data such as bio, timezone, location, email, and model/provider metadata that are not necessary for solving or learning about the Hodge Conjecture. This creates avoidable privacy risk and expands the amount of sensitive user context transmitted to an 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 153)May include surrounding context.

This is where Millennium: Hodge Conjecture — Does Topology Remember Algebra? begins.

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

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description includes English, Chinese, and Spanish text in a single user-facing field, but does not indicate that multilingual output is optional or user-selected. This can violate a language or locale policy requiring user opt-in before forcing a specific language or mixed-locale experience.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Submitting and reading reviews is a community/content feature, not a direct requirement for delivering a multi-day interactive mathematics journey. Because the manifest only describes the educational experience itself, this additional remote publishing capability is not justified by the stated purpose.

Content

No source excerpt is available for this finding.