audit-sql
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external codebase content which creates a surface for indirect prompt injection.
- Ingestion points: The instructions direct the agent to search for and read DDL schema files (e.g.,
*.sql) and MyBatis mapper XML files from the project directory. - Boundary markers: There are no specific boundary markers or delimiters defined to isolate the content of these files when they are processed by the agent.
- Capability inventory: The skill utilizes file searching and reading capabilities to gather data for analysis.
- Sanitization: The instructions do not include steps to sanitize or validate the content of the discovered files before the agent analyzes them, allowing potentially malicious instructions inside SQL comments or XML metadata to influence the audit process.
Audit Metadata