litestar-data-services
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a technical styleguide for developers working with the Litestar framework. It provides code examples for Controller and Service layers using well-known libraries such as SQLAlchemy and Advanced Alchemy.
- [INDIRECT_PROMPT_INJECTION]: As a code generation and architectural skill, it possesses an attack surface for indirect prompt injection if user-provided model names or requirements contain malicious instructions.
- Ingestion points: The skill processes user-defined model names, field names, and service requirements to generate code templates (e.g.,
UserService,User). - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are present in the provided templates to isolate user-supplied data from generated code.
- Capability inventory: The skill itself does not have file-write, network, or subprocess capabilities; it only provides instructions and templates for the agent to follow.
- Sanitization: No explicit sanitization of user-provided identifiers is documented within the skill's instructions.
- [EXTERNAL_DOWNLOADS]: The skill references official Litestar documentation and a third-party repository (
github.com/cofin/litestar-sqlstack) as a source for a manual code pattern. These are presented as educational references for the developer to use manually rather than automated execution paths for the agent.
Audit Metadata