build-prototype
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [SAFE]: The skill instructions provide clear security boundaries by explicitly prohibiting the inclusion of real data, APIs, production code, and network dependencies in the prototypes.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files to populate prototype content. 1. Ingestion: Reads GLOSSARY.md and docs/decisions/README.md as described in SKILL.md. 2. Boundary markers: Delimiters are not specified for the interpolation of these files. 3. Capability inventory: Writing HTML and Markdown files as specified in SKILL.md. 4. Sanitization: No explicit sanitization of input data is required. The risk is considered minimal due to the isolated nature of the artifacts.
- [DYNAMIC_EXECUTION]: The agent generates interactive HTML files by populating templates with JavaScript. Evidence: Usage of templates/shell.html and templates/comparison-shell.html to create functional UI mockups. This execution is confined to the browser for demonstration purposes.
Audit Metadata