network-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external network configurations and monitoring data, creating a surface for potential indirect prompt injection attacks. \n
- Ingestion points: The skill is designed to analyze network configurations, documentation, and monitoring logs (e.g., flow logs, packet captures) as specified in the 'Tool Restrictions' and 'Monitoring and Troubleshooting' sections.\n
- Boundary markers: There are no explicit delimiters or instructions defined to isolate untrusted data from the system prompt or to ignore embedded commands.\n
- Capability inventory: The skill possesses the ability to execute 'bash' commands for diagnostics and 'write' files for infrastructure-as-code templates, which increases the potential impact if a prompt injection occurs.\n
- Sanitization: The skill description does not specify any validation, filtering, or sanitization routines for handling external content before it is processed by the agent.
Audit Metadata