scan-cyber-threats
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to the
worldmonitor.appAPI to retrieve cyber-threat intelligence data, including indicators of compromise and command-and-control server details. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from public threat feeds. While the skill includes explicit guardrails instructing the agent not to navigate to or interact with the indicator values (which represent live malware infrastructure), the processing of this third-party content constitutes an inherent attack surface.
Audit Metadata