siyu-wenzhen
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted business descriptions and data from users to provide diagnostic advice. While this creates a potential surface for indirect prompt injection, the skill's capabilities are limited to providing text-based consultation and referencing internal knowledge files, posing minimal risk.
- Ingestion points: User-provided business scenarios, goals, and status reports (processed in SKILL.md).
- Boundary markers: Absent. The instructions do not specify the use of delimiters for user-provided data.
- Capability inventory: Natural language generation and internal tool invocation (e.g., siyu-market-research). No file system modifications or network exfiltration capabilities are present in the analyzed file.
- Sanitization: Not explicitly defined in the instructions.
Audit Metadata