awesome-db-audit
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from the repository, including database schemas and source code queries.
- Ingestion points: The skill reads schema files, ORM models, migration directories, and query sites within the local codebase (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to the agent to isolate external data from its core instructions to prevent accidental obedience to embedded strings.
- Capability inventory: The skill utilizes file system read access and optional read-only database connections. It uses 'ripgrep' for static analysis. No outbound network or file-write capabilities are defined.
- Sanitization: The instructions do not specify any sanitization, validation, or escaping logic for the content read from the codebase.
Audit Metadata