Security audit

digital-human-training

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for digital-human setup; it is coherent with its purpose but should give stronger consent and biometric privacy warnings.

Before using this skill, only train on voice or face recordings from people who clearly consent, keep the recordings and generated models private, define deletion/retention practices, and avoid deploying a clone that could impersonate someone without authorization.

A.I.G

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

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The document instructs users to provide a one-minute voice recording and a 30-second face video to build a digital human, but it does not warn that these are sensitive biometric identifiers or advise on consent, retention, or misuse risks. In this skill context, the omission is more dangerous because the collected data directly enables voice cloning and facial reenactment, which can facilitate impersonation, fraud, and non-consensual identity replication.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The natural-language content of the skill, including its description, headings, and example usage, is presented only in Chinese. This can constitute a language/locale policy issue because the skill implicitly forces a specific language without stating that users can choose another language.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: Most instructional text in the file is written in Chinese, and the document does not offer an alternative language or indicate that the language choice is optional. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.