replica-build
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from reconnaissance files and design documents to drive code generation, creating a surface for indirect prompt injection attacks.
- Ingestion points: Reads project reconnaissance data from
replica/recon.md,replica/architecture.md, and visual design references fromreplica/design/. - Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings for the data being ingested and processed.
- Capability inventory: The agent is authorized to write new source code files, update CSV feature matrices, and maintain build logs.
- Sanitization: There are no documented steps for validating or sanitizing the content of the design specifications before they are translated into executable code.
Audit Metadata