opc-mvp-designer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill operates exclusively on local project files within the
opc-doc/directory and requires explicit user confirmation before persisting any data. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface as it reads data from local project files.
- Ingestion points: Reads from
opc-doc/outputs/04-business-model/risky-assumptions.md. - Boundary markers: None explicitly defined for the file content.
- Capability inventory: Restricted to writing Markdown and JSON files within the local project workspace.
- Sanitization: Employs a mandatory human-in-the-loop confirmation step ('用户确认后再写入正式结果') before any file-writing operations are performed.
Audit Metadata