skills/brhiza/mingyu/aov-mingyu-api/Gen Agent Trust Hub

aov-mingyu-api

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [DATA_EXFILTRATION]: The skill is designed to transmit user-provided personal information, such as birth names, dates, times, and geographic coordinates, to an external API at aov.cc for processing.
  • [INDIRECT_PROMPT_INJECTION]: User-provided questions and message history are interpolated into API requests and processed by a downstream AI model, presenting a risk of indirect prompt injection.
  • Ingestion points: User input for the question parameter in various /prompt endpoints and the messages array in the /ai/analyze endpoint.
  • Boundary markers: The instructions do not specify the use of clear delimiters or guardrails to separate user input from the surrounding prompt framework.
  • Capability inventory: The skill possesses network capabilities to communicate with the aov.cc API.
  • Sanitization: The API documentation lists character limits (e.g., 5000 characters for questions) and message count limits for the AI analysis endpoint.
  • [EXTERNAL_DOWNLOADS]: The skill relies on communication with the external, non-whitelisted domain aov.cc for all calculation and analysis functions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 12:37 PM
Security Audit — agent-trust-hub — aov-mingyu-api