axiom-grdb
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the official GitHub repositories for the
GRDB.swiftandGRDBQuerylibraries for integration and documentation.\n- [COMMAND_EXECUTION]: Provides implementation details and code snippets for executing raw SQL queries and managing database migrations on local SQLite database files.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for data ingestion from local databases, which constitutes a potential attack surface if processed data influences future agent actions.\n - Ingestion points: Data is retrieved from the database using
Track.fetchAll,Row.fetchAll, andValueObservationpatterns inSKILL.md.\n - Boundary markers: The provided examples utilize SQL parameterization (
?placeholders andargumentsarrays) to ensure safe input handling within queries.\n - Capability inventory: The skill includes capabilities for reading and writing to the local file system to maintain the SQLite database.\n
- Sanitization: Standard SQL parameterization is consistently demonstrated in all query examples to prevent injection vulnerabilities.
Audit Metadata