network-appliance-attacks
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard network diagnostic tools such as ike-scan and openssl to evaluate perimeter appliance configurations. These tools are used for their intended purpose of protocol enumeration and posture checking, and the skill provides specific commands focused on information gathering rather than exploitation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from potentially untrusted external sources, including device banners and cryptographic handshake responses. While this constitutes an ingestion surface for external data, the risk is mitigated by explicit instructions to verify findings through multiple sources (infer, don't assume) and an awareness that external indicators like banners can be spoofed or misleading.
Audit Metadata