sql-schema-audit
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (SQL schema files, query catalogs, and source code files) to generate audit reports, creating a potential vector for indirect prompt injection.
- Ingestion points: The scripts
scripts/index-coverage.mjsandscripts/n-plus-one.mjsread arbitrary files from the filesystem based on user-provided paths. - Boundary markers: The skill does not employ delimiters or specific warnings to the agent to ignore instructions that might be embedded within the files being audited.
- Capability inventory: The skill can read local files, write audit reports to the filesystem (
--outparameter), and execute SQL commands in an in-memory SQLite database vianode:sqlite. - Sanitization: The skill executes SQL schema definitions directly using
db.exec()without sanitization to establish the audit environment.
Audit Metadata