checklist
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data such as database schemas and migration files. This introduces an indirect prompt injection surface where malicious content in those files could attempt to influence the agent's logic. However, the skill is strictly defined as read-only, which significantly mitigates the potential impact of such an attack.\n
- Ingestion points: Repository files (schema, ORM, migrations) and live database metadata.\n
- Boundary markers: Not present; the skill lacks explicit instructions to treat the ingested code as data only.\n
- Capability inventory: Access to Read, Grep, Glob, Bash, and Task tools.\n
- Sanitization: No explicit sanitization or validation of the ingested files is mentioned.
Audit Metadata