wechat-top-account

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill facilitates legitimate data retrieval from doubaoya.com, consistent with its declared purpose of WeChat account tracking.
  • [EXTERNAL_DOWNLOADS]: The skill connects to the vendor's API at doubaoya.com to retrieve ranking data. This connection is necessary for the skill's function and targets the official service domain.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: Authentication is handled via the environment variable DOUBAOYA_API_KEY. The skill instructions include explicit guidelines to prevent the AI agent from leaking or exposing these credentials in its responses, adhering to secure secret management practices.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the Doubaoya API. Ingestion point: API response output from scripts/fetch_index_rank.py. Boundaries: The instructions define specific fields for extraction (rank, accountName, indexScore). Capability inventory: The agent executes the data-fetching script and renders a Markdown table. Sanitization: The skill uses structured JSON parsing which reduces risk, though no explicit filtering of the data content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 11:44 AM
Security Audit — agent-trust-hub — wechat-top-account