feature-tech-design
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes untrusted local files as input.\n
- Ingestion points: The skill reads requirements from
docs/{功能名称}/1_需求文档.mdand UI prototypes fromdocs/{功能名称}/prototypes/*.html.\n - Boundary markers: No explicit delimiters are used to separate ingested data from the agent's core instructions.\n
- Capability inventory: The skill is capable of writing technical documentation to the local file system at
docs/{功能名称}/2_技术方案.md.\n - Sanitization: No input validation or sanitization is performed on the ingested content.\n
- Mitigation: Implement strict boundary delimiters and include instructions for the agent to treat all ingested file content as passive data, ignoring any embedded commands.
Audit Metadata