mp-checkout-bricks
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a legitimate technical integration guide for Mercado Pago payment components. All instructions, code snippets, and documentation are consistent with official Mercado Pago developer resources.
- [DATA_EXFILTRATION]: No evidence of unauthorized data access or exfiltration. The skill includes explicit security warnings (e.g., in
references/rules-preference.md) stating that the AI agent must never handle or receive sensitive credentials like theACCESS_TOKENdirectly. - [EXTERNAL_DOWNLOADS]: The skill references official and trusted Mercado Pago resources, such as the JS SDK via
https://sdk.mercadopago.com/js/v2and standard packages from NPM (@mercadopago/sdk-js) and PyPI (mercadopago). No suspicious or unverified external sources are utilized. - [REMOTE_CODE_EXECUTION]: No unauthorized remote code execution patterns were detected. The technical snippets provided are standard integration code for frontend (JS/React) and backend environments.
- [PROMPT_INJECTION]: The skill does not contain any instructions that attempt to bypass AI safety guardrails, override system prompts, or extract internal configuration.
Audit Metadata