polardbx-ttl20
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-supplied database schemas to generate SQL statements.
- Ingestion points: User-provided CREATE TABLE statements (SKILL.md, references/ttl20-user-guide.md).
- Boundary markers: None present.
- Capability inventory: No tool access or shell execution capabilities are defined or used; the skill only generates text output.
- Sanitization: None present.
- [SAFE]: Static detections for concealment were evaluated as false positives. Phrases such as 'metadata-only change' and 'async, long-running' correctly describe the performance characteristics of PolarDB-X database operations and are not attempts to hide malicious agent behavior.
Audit Metadata