requirement-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a wide variety of untrusted external data sources which could contain hidden instructions intended to manipulate the agent's output or logic.
- Ingestion points: Processes PRD documents, technical designs, API documentation, Bug/Issue reports, and source code repositories as specified in the 'Input' and 'Workflow' sections.
- Boundary markers: The workflow includes a mandatory 'Clarification' step (⏸ 检查点) where the agent must stop and ask the user for confirmation when encountering ambiguities or conflicts, providing a manual control against adversarial input.
- Capability inventory: The skill's primary capability is reading files and writing a structured Markdown requirement model (
需求模型.md). It does not demonstrate network exfiltration or shell execution capabilities in this specific instruction file. - Sanitization: There is no mention of automated sanitization or filtering of the content extracted from external documents; reliance is placed on the user's manual review during clarification.
Audit Metadata