database-migration-integrity-checker
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external SQL migration files, which constitutes a potential surface for indirect prompt injection. Attackers could embed instructions within SQL comments or literals intended to manipulate the agent's auditing logic or output.
- Ingestion points: Reads files from the directory path provided in the
migration_files_pathinput (defined inskill.yaml). - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are defined in the provided configuration.
- Capability inventory: The skill manifest indicates capabilities for reading file content and providing audit results; it does not request dangerous capabilities such as network access, shell execution, or sensitive file system writes.
- Sanitization: There is no evidence of sanitization or filtering of the SQL file content before it is processed by the agent.
Audit Metadata