dbs-chatroom-austrian
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues, malicious code, or unauthorized data access patterns were detected. The skill's behavior aligns with its described purpose.
- [PROMPT_INJECTION]: The skill uses a multi-agent workflow that ingests user input and interpolates it into prompts for sub-agents (Hayek and Mises). This represents an indirect prompt injection surface. Ingestion points: User input is captured via
{用户问题}in Phase 2 and Phase 4. Boundary markers: There are no explicit delimiters or safety instructions wrapping the user input within the sub-agent prompts. Capability inventory: The skill has no access to sensitive files, network operations, or shell execution tools. Sanitization: No sanitization or validation of user-provided input is performed. Given the lack of dangerous capabilities, this surface is assessed as low risk.
Audit Metadata