aionui-webui-public

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the cloudflared binary from the official Cloudflare GitHub repository. This is a common practice for obtaining the tool and utilizes a well-known, established source.
  • [COMMAND_EXECUTION]: The skill uses shell commands to manage local services and install required tools. These actions are directly related to the skill's primary function of setting up a tunnel.
  • [DATA_EXFILTRATION]: The skill is designed to expose a local service to the internet using a Cloudflare tunnel. While this involves routing local traffic to a public URL, the skill provides extensive documentation on the associated security risks, TLS termination at the edge, and password requirements.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection when processing user-supplied credentials for local API updates. Ingestion points: User-provided username and password for the AionUi WebUI in the optional credential change step. Boundary markers: No explicit markers are present in the command templates. Capability inventory: The skill has the ability to execute shell commands and perform network requests. Sanitization: The skill relies on the agent to correctly interpolate and sanitize user input before command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 08:33 AM
Security Audit — agent-trust-hub — aionui-webui-public