didit-aml-screening
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill communicates with the vendor's official API endpoint (https://verification.didit.me/v3/aml/) to perform anti-money laundering checks. This network activity is documented, targets the vendor's own infrastructure, and is required for the skill's primary function.
- [PROMPT_INJECTION]: The skill processes user-supplied data such as full names, dates of birth, and document numbers. While this data is passed to an external API, it is treated as data for screening purposes and is not used to execute commands or influence the agent's internal instructions.
- [COMMAND_EXECUTION]: The skill includes a utility script (scripts/screen_aml.py) that allows users to perform screenings from the command line. This script uses standard Python libraries and does not involve unsafe subprocess calls or dynamic code execution.
Audit Metadata