Didit Biometric Age Estimation

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:13 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed Didit age-estimation helper that uploads user-selected face images, but it needs careful privacy, consent, and retention handling.

Install only if you intend to send facial images to Didit for biometric age estimation. Confirm you have user consent and a legal basis, protect DIDIT_API_KEY, avoid personal identifiers in vendor_data, and set request-saving or retention behavior deliberately. Do not rely on the sample CLI alone for regulated age-gating until you have implemented threshold, liveness, fallback, regional policy, and response-schema checks.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 86% confidence
• Finding: The skill requires environment access for `DIDIT_API_KEY` and makes outbound network requests, but it does not declare corresponding permissions. Undeclared capabilities reduce transparency and can undermine platform security controls, making it harder for users or policy engines to assess what the skill can access.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 84% confidence
• Finding: The skill advertises passive liveness, adaptive ID fallback, and per-country restrictions as capabilities, but the concrete examples only perform a basic age-estimation upload. This mismatch can cause integrators to rely on security/compliance controls that are not actually implemented, leading to underage access or failed regulatory enforcement.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill sends facial images and derived biometric/age-estimation data to an external service, and the request parameter table indicates `save_api_request` defaults to `true`, meaning submissions may be retained. Failing to warn users about external biometric processing and default retention creates serious privacy, consent, and compliance risks, especially for minors and age-gating use cases.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The script uploads a facial image and optional vendor tracking data to a third-party biometric verification API, but the CLI does not present a clear runtime disclosure, consent prompt, or minimization guidance. Because facial images are highly sensitive biometric data, silent transmission can create privacy, compliance, and user-trust risks, especially in age-gating or regulatory contexts.

VirusTotal

64/64 vendors flagged this skill as clean.