xiaohongshu-dailytop

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow fetches Xiaohongshu note data (including titles and descriptions authored by platform users) from the RedFox API via scripts like xhs_daily_fetcher.py and ingests this outsider-authored text into the agent context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime HTTP requests to an external API (redfox.hk) to fetch data, but official platform ownership and strong provenance for RedFox Hub cannot be verified under strict provenance rules.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 0.70). The skill documents a direct financial operation: recharging API credits via Alipay (cashierUrl, submit-payment, poll-payment-status) when facing a balance shortage. However, no independent access control (such as service-enforced multi-factor authentication or server-side authorization checks) is documented for initiating or executing this payment flow. Therefore, it falls under direct operations without established qualifying control.