create-prototype
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could contain malicious instructions to influence the agent's code generation behavior.
- Ingestion points: The skill reads
user_storyvariables and files located in.agents/flow/(JSON/Markdown PRDs). - Boundary markers: Absent. There are no explicit delimiters or instructions to ignore commands embedded within the user story or PRD data.
- Capability inventory: The agent has the ability to create and modify files within the project workspace.
- Sanitization: Absent. The skill does not perform validation or filtering on the content of the ingested requirement documents.
Audit Metadata