sumsub-create-aml-resolution-rules
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
subprocess.runwithinscripts/aml_rules_api.pyto executecurlfor API requests. The command is constructed as a list of arguments, which is a secure implementation that prevents shell command injection. - [EXTERNAL_DOWNLOADS]: API calls are made to
api.sumsub.comfor rule management. These are legitimate operations targeting the vendor's official infrastructure. - [INDIRECT_PROMPT_INJECTION]: While the skill ingests external rule metadata, it utilizes a validation script (
scripts/build_aml_rule.py) that enforces a strict JSON schema and operator whitelist, preventing malicious data from influencing the agent's logic flow. - [SAFE]: The skill proactively mitigates risks by requiring AI-specific App Tokens and enforcing a sandbox-only restriction for credentials unless explicitly overridden by the user.
Audit Metadata