macro-monitor
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's operations are consistent with its stated purpose of monitoring economic data. It accesses reputable sources such as the Federal Reserve (FRED), Trading Economics, and official Chinese government portals.\n- [COMMAND_EXECUTION]: The skill utilizes the browser tool to navigate to specific, well-known financial and regulatory URLs. These actions are limited to the intended data collection scope.\n- [DATA_EXFILTRATION]: No unauthorized data transmission was detected. The skill summarizes publicly available information and delivers it to the user via the message tool.\n- [PROMPT_INJECTION]:\n
- Ingestion points: External data is ingested from multiple external websites including Trading Economics, FRED, and news portals (Caixin, WallStreetCN) via the browser tool.\n
- Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands in the ingested web content.\n
- Capability inventory: The skill uses browser for web access, read for local file access, and has instructions to update its local knowledge base (write), alongside message for user output.\n
- Sanitization: No specific sanitization or validation of the ingested content is defined before the agent processes and summarizes it.
Audit Metadata