alibabacloud-migration-lhm-inspect-hive-metastore
Fail
Audited by Snyk on Aug 4, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The skill includes plaintext password placeholders in config/scripts (e.g., MYSQL_PASSWORD and config.ini) and CLI examples that pass --password, which would require the agent to insert or echo user secrets verbatim into commands/files — an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s runtime ingests Hive Metastore free-text metadata (e.g., partition values, table/column comments, SerDe/TBLPROPERTIES values) fetched from the Hive Metastore via Thrift/DB and then feeds it into the LLM through DDL reconstruction paths (e.g.,
hive_dive_thrift.py→ddl_builder.py), without selecting specific pre-trusted items first.
Issues (2)
W007
HIGHInsecure credential handling detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata