byted-vedb-mysql
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates cloud resource management through the official
volcengine-python-sdk, interacting with legitimate Volcengine API endpoints. - [SAFE]: Sensitive credentials such as
VOLCENGINE_ACCESS_KEYandVOLCENGINE_SECRET_KEYare managed via environment variables and '.env' files, conforming to secure configuration management practices. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data by reading responses from Volcengine cloud APIs (documented in
list_instances.py,describe_instance.py, andlist_db_accounts.py). These outputs are interpolated into the agent's context without explicit boundary markers or sanitization logic, creating a surface where responses from the external API could influence agent behavior.
Audit Metadata