build-prototype
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project files such as documentation and design tokens, which could potentially contain malicious instructions meant to influence the agent's behavior.
- Ingestion points: The skill is instructed to read
GLOSSARY.md,docs/decisions/README.md, work-unit specifications, and project-specific design system files (tokens and components). - Boundary markers: There are no explicit instructions to wrap the ingested content in delimiters or to ignore any embedded instructions found within these files.
- Capability inventory: The skill has file-writing capabilities (creating
prototype.html,compare.html, and documentation underdocs/specs/) and the ability to delegate tasks to subagents. - Sanitization: No sanitization or validation of the ingested external content is described before it is processed or used to generate output.
Audit Metadata