improve-codebase-architecture
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface as it is designed to ingest and process untrusted codebase content.
- Ingestion points: The skill reads the project's domain glossary, ADR documents, and entire codebase using an exploration sub-agent.
- Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded in the analyzed code or documentation.
- Capability inventory: The skill has read access to the entire repository and the ability to update or create documentation files such as CONTEXT.md and ADRs.
- Sanitization: No sanitization or validation of the ingested content is specified before it is used to generate suggestions or update project files.
Audit Metadata