ln-71-system-design-baseline-builder
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill defines a controlled workflow for system design documentation. It uses a structured checklist to ensure architecture drivers are evidenced and recorded appropriately without introducing arbitrary execution risks.
- [DATA_EXPOSURE]: The skill interacts with repository artifacts, such as requirements, security docs, and Git state, to gather context. This access is limited to the local project environment and is necessary for its stated purpose of creating a durable source of truth for the project.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external repository data which could theoretically contain malicious instructions.
- Ingestion points: Existing requirements, architecture artifacts, SLOs, and repository metadata (Step 1 and 2).
- Boundary markers: The skill encourages the preservation of existing content and unambiguous document selection but lacks specific 'ignore instruction' delimiters for ingested text.
- Capability inventory: Capabilities are limited to native file reads, repository searches, and writing a single documentation artifact at
docs/architecture/system-design-baseline.md. - Sanitization: No explicit sanitization or validation of the ingested text is described.
- [NO_CODE]: This skill contains only Markdown instructions and process logic. It does not include or execute any external scripts, binaries, or package installations.
Audit Metadata